Search

This paper presents a decision-making approach grounded in rough set theory and evidential reasoning to address the demand for expert decision-making in greenhouse environmental control systems. Furthermore, a decision-making model is developed by integrating the D-S evidence theory with an expert knowledge table for greenhouse environmental control systems. The model's reasoning process encompasses continuous attribute discretization, expert decision table formation, attribute reduction, and evidence combination reasoning. Firstly, the fuzzy C-means clustering algorithm is employed to discretize the original environmental data and cluster it. Subsequently, an attribute reduction algorithm based on information entropy is utilized to optimize the decision table by eliminating unnecessary conditional attributes in expert knowledge. The reduced indicators are then combined using evidential theory. Finally, suitable greenhouse control methods are determined by the confidence decision proposed by the D-S evidence theory. To assess the efficacy of this intelligent decision-making algorithm based on rough set and D-S evidence theory, its performance is compared with traditional SVM algorithms and small-shot learning algorithms. The results indicate that this proposed method significantly enhances the credibility of control decision-making processes, with an average running time of 0.002378s for the fusion decision algorithm and 0.017939s for the support vector machine (SVM) algorithm, respectively. The SVM accuracy rate after testing and training stands at 90.34%. Moreover, retraining based on information entropy attribute reduction leads to a correct decision rate increase of up to 100%. This method notably improves confidence levels in decision-making processes while reducing uncertainty and demonstrates reliability when applied in making decisions regarding greenhouse environments. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is evolving rapidly and has made many theoretical breakthroughs while widely applied in various fields. ML allows systems the ability to access data and use it to enable computers to execute cognitive processes such as learning and improving from previous experiences and solving complicated issues. Many first-order stochastic optimization methods have been used to solve the optimization model of ML. These algorithms adopt Barzilai-Borwein (BB) step size instead of fixed or diminishing step size to improve performance. However, the BB step size format involves fractional calculation, which inevitably leads to a zero denominator, especially when the objective function is non-convex. The BB technique will be violated if the denominator is near 0 or even negative. To improve the computation of the step size, a Positive Defined Stabilized Barzilai-Borwein (PDSBB) approach is introduced in this paper. Integrating PDSBB with the stochastic variance reduced gradient (SVRG) approach, a new method SVRG-PDSBB is proposed. Numerical experiments have shown that the new algorithm has stabilized the performance of the new step size, which successfully avoiding zero denominators and effectively solving the common problems in machine learning. The convergence of SVRG-PDSBB is theoretically and numerically proven, and the effectiveness of the new algorithm is shown by comparison with other algorithms. [ABSTRACT FROM AUTHOR]

Virtualization technology makes cloud resources affordable. Virtual Machines (VMs) are widely used on top of host machines in cloud computing environments. Adversaries target L3 cache memory in such environments as VMs shared L3 cache of the physical machine. Cache side-channel attacks are possible unless there are mechanisms in place to prevent them. The attacker compromises a VM and through which tries to extract sensitive information from the victim's machine. In the literature, many solutions are found to resist cache side-channel attacks. However, an important limitation of the existing approaches is that they are not real-time in nature. In this paper, we proposed a security framework for improving Quality of Service (QoS) by detecting and mitigating cache side-channel attacks in virtualized environments. Two algorithms are proposed to realize the framework. They are known as Softmax Function-Based Machine Learning for Side-Channel Attack Monitoring (SFML-SCAM) and Intelligent Noise Addition for Attack Mitigation (INA-AM). The first algorithm takes care of monitoring and detecting cache sidechannel attacks and notifying administrators while the second one is responsible to mitigate the effects of attacks. A machine learning technique assists the SFML-SCAM in detecting attacks based on the abnormality in the CPU counters in realtime. The INA-AM algorithm, on the other hand, has a strategy to add noise to the cache data to deceive the attacker and mitigate the effects of the attack. Experiments are made with open-source tools along with a prototype that implements the proposed algorithms. Information leakage is evaluated for all detection methods against stealth attacks. Experimental results revealed that the proposed framework outperforms the state-of-the-art. [ABSTRACT FROM AUTHOR]

The simulated annealing algorithm is a stochastic optimization method for solving optimization problems associated with a large search space. The efficiency of the algorithm depends on the adaptation of the cooling model. Despite this, the main disadvantage of this algorithm is that it does not take into account the state of the system while searching. Thus, it is difficult to predict the system convergence with the simulated annealing algorithm. However, neural networks in particular continuous Hopfield networks have proven their ability in the field of machine learning to make a decision. In this paper, we introduce continuous Hopfield networks to improve the convergence of the simulated annealing algorithm. The experimental results show that the hybrid approach produces a large number of stable sets. [ABSTRACT FROM AUTHOR]

This paper presents a metaheuristic with online learning (MOL) to solve the multi-school heterogeneous-fleet school bus routing problem (MHSBRP). In the iterated local search (ILS) metaheuristic framework, an online learning mechanism is integrated with the neighborhood search heuristic. It evaluates the performance of search operators according to the historical search information, and then adjusts the selection probability of the operators in the following loops of search. The proposed algorithm is tested on a set of benchmark instances. The solution results show that MOL solves both mixed-load and single-load instances of MHSBRP effectively, and outperforms the ILS significantly. Compared with the algorithm without learning mechanism, MOL could improve the convergence of neighborhood search and the quality of solution. [ABSTRACT FROM AUTHOR]