The accuracy of predicting river-suspended sediment concentration (SSC) is crucial for evaluating the functional lifespan of reservoirs, analyzing river geomorphological evolution, and assessing riverbed stability. In...
详细信息
The accuracy of predicting river-suspended sediment concentration (SSC) is crucial for evaluating the functional lifespan of reservoirs, analyzing river geomorphological evolution, and assessing riverbed stability. In this study, we aim to develop new models for SSC prediction at two hydrological stations near Puerto Rico, USA, by integrating the bacterial foraging optimization algorithm and adaptive neural fuzzy inference network (ANFIS). The models comprise ANFIS with grid partition (ANFIS-GP), ANFIS with subtractive clustering (ANFIS-SC), and ANFIS with fuzzy c-means clustering (ANFISFCM). Additionally, we employ an artificial neural network (ANN) and the sediment rating curve (SRC) for predicting daily series data of flow discharge-suspended sediment concentration (SSC). Different scenarios are considered based on varying input and output variables, leading to predictions for four distinct scenarios. At the Rio Valenciano Station, the MRSE values for ANFIS-BFO, ANFIS-FCM, ANFIS-GP, ANFIS-SC, ANN, and SRC are 2.2172, 2.5389, 2.6627, 2.7549, 2.7994, and 3.7882, respectively. For the Quebrada Blanca Station, the MRSE values for ANFIS-BFO, ANFIS-FCM, ANFIS-SC, ANFIS-GP, ANN, and SRC are 0.8295, 0.8664, 0.8964, 0.9110, 0.9684, and 1.6742, respectively. It can be inferred that ANFIS-BFO exhibits superior prediction results compared to all other models. Furthermore, ANFIS-SC and ANFIS-FCM demonstrate slightly better prediction performance than ANFIS-GP. In comparison to ANN, ANFIS-GP, ANFIS-SC, and ANFIS-FCM exhibit slightly superior prediction performance.
With the rapid development of artificial intelligence and data science, Dynamic Bayesian Network (DBN), as an effective probabilistic graphical model, has been widely used in many engineering fields. And swarm intelli...
详细信息
With the rapid development of artificial intelligence and data science, Dynamic Bayesian Network (DBN), as an effective probabilistic graphical model, has been widely used in many engineering fields. And swarm intelligence algorithm is an optimizationalgorithm based on natural selection with the characteristics of distributed, self-organization and robustness. By applying the high-performance swarm intelligence algorithm to DBN structure learning, we can fully utilize the algorithm's global search capability to effectively process time-based data, improve the efficiency of network generation and the accuracy of network structure. This study proposes an improved bacterial foraging optimization algorithm (IBFO-A) to solve the problems of random step size, limited group communication, and the inability to maintain a balance between global and local searching. The IBFO-A algorithm framework comprises four layers. First, population initialization is achieved using a logistics-sine chaotic mapping strategy as the basis for global optimization. Second, the activity strategy of a colony foraging trend is constructed by combining the exploration phase of the Osprey optimizationalgorithm. Subsequently, the strategy of bacterial colony propagation is improved using a "genetic" approach and the Multi-point crossover operator. Finally, the elimination-dispersal activity strategy is employed to escape the local optimal solution. To solve the problem of complex DBN learning structures due to the introduction of time information, a DBN structure learning method called IBFO-D, which is based on the IBFO-A algorithm framework, is proposed. IBFO-D determines the edge direction of the structure by combining the dynamic K2 scoring function, the designed V-structure orientation rule, and the trend activity strategy. Then, according to the improved reproductive activity strategy, the concept of "survival of the fittest" is applied to the network candidate solution while maintaining spec
To improve the stability and smoothness of bionic lower extremity exoskeleton walking gait, the elitist mechanism was introduced to enhance the diversity and improve the search ability of the optimal solution. The sim...
详细信息
To improve the stability and smoothness of bionic lower extremity exoskeleton walking gait, the elitist mechanism was introduced to enhance the diversity and improve the search ability of the optimal solution. The simulation analyses showed that the improved bacterialforagingalgorithm had higher convergence accuracy, and was not easy to fall into local extremum. The improved foragingoptimizationalgorithm was used for the optimization of the bionic lower extremity exoskeleton gait zero moment point stability margin. The simulation results showed that the optimal gait planning method proposed can increase the stability margin and ensure the stable and smooth walking.
bacterial foraging optimization algorithm (BFO) is a swarm intelligence-based optimizationalgorithm that has been widely applied in various fields. However, the classical BFO still suffers from two major limitations:...
详细信息
ISBN:
(纸本)9789819771806;9789819771813
bacterial foraging optimization algorithm (BFO) is a swarm intelligence-based optimizationalgorithm that has been widely applied in various fields. However, the classical BFO still suffers from two major limitations: The fixed chemotactic step-size makes it difficult to balance exploration and exploitation capabilities, and the non-elitist elimination strategy in the reproduction phase may lead the population to be trapped in local optima. To address the two limitations of the classical BFO, this paper presents an improved BFO with adaptive chemotactic step-size and chaos-enhanced non-elite reverse learning (CLBFO). In CLBFO, the chemotactic step employs an adaptive nonlinear dynamic step-size strategy. Each bacterial individual adaptively selects an appropriate chemotactic step-size at different stages of the optimization process, which effectively alleviates the low search efficiency and oscillation problems caused by the fixed step-size. The reproduction step improves the non-elite solutions based on non-elite reverse learning and incorporates a chaotic disturbance mechanism to enhance the convergence speed and effectively reduce the possibility of the population falling into local optima. The performance of the proposed algorithm was evaluated on the benchmark test suite and compared with that of other intelligent optimizationalgorithms. The comparisons demonstrated the effectiveness of the proposed algorithm in balancing exploration and exploitation, and reducing the risk of local convergence.
In this article, bacterialforagingoptimization (BFO) algorithm is developed for double sided optimal bidding strategy in an electricity market. Optimal bidding strategy is one of the important functions in the elect...
详细信息
In this article, bacterialforagingoptimization (BFO) algorithm is developed for double sided optimal bidding strategy in an electricity market. Optimal bidding strategy is one of the important functions in the electricity market along with forecasting of the electricity price and the profit based unit commitment. The prime objective of generating company (Genco) and distribution company (Disco) is to maximize their profit when they participate in the bidding process. Two stages are involved in the proposed approach. In the first stage, the BFO algorithm has been used to maximize the probability density function (pdf). In the second stage the BFO algorithm is again applied to maximize the profit of the GENCO and DISCO. The Proposed algorithm is developed in MATLAB (Version, 2019) and tested on standard test case available in the literature. Also, the simulation results are presented and compared. It is noticed that the proposed method yields the best results in terms of profit.
The layout design of user interface (UI) is a key issue in making a better human-computer interaction system for complex system such as spacecraft or vehicles, which directly affects the information level, tactical pe...
详细信息
ISBN:
(纸本)9781728165974
The layout design of user interface (UI) is a key issue in making a better human-computer interaction system for complex system such as spacecraft or vehicles, which directly affects the information level, tactical performance and operational efficiency. Firstly, this study builds a model for the layout design of UI which concerns the importance and use frequency of the layout components. Then, an improved bacterial foraging optimization algorithm is proposed to solve the layout optimization problems, which include the process of chemotaxis, replicates and migration. The preliminary results showed the feasibility of the proposed method.
Softmax regression is a supervised multi-class nonlinear classification algorithm in machine learning. Sometimes it is also used in regression problems. It is mainly used in transfer learning, knowledge distillation a...
详细信息
ISBN:
(纸本)9780738111353
Softmax regression is a supervised multi-class nonlinear classification algorithm in machine learning. Sometimes it is also used in regression problems. It is mainly used in transfer learning, knowledge distillation and meta learning in artificial intelligence. Softmax optimizer is gradient descent method or random gradient descent method, but its loss function is a multi peak, strong nonlinear function, and the optimal solution is only the local optimal solution rather than the global optimal solution, and depends on the gradient. So we use a swarm intelligence optimizationalgorithm which is independent of gradient and can find the global optimal solution to optimize This article will introduce the bacterial foraging optimization algorithm.
The flexible job-shop scheduling problem (FJSP) is an extension of the classical job-shop scheduling problem (JSP) in which operations can be performed by a set of candidate capable machines. An extended version of th...
详细信息
The flexible job-shop scheduling problem (FJSP) is an extension of the classical job-shop scheduling problem (JSP) in which operations can be performed by a set of candidate capable machines. An extended version of the FJSP, entitled sequencing flexibility, is studied in this work, which considers precedence between the operations in the form of a directed acyclic graph instead of a sequential order. In this work, a mixed integer linear programming (MILP) formulation is presented to minimize weighted tardiness for the FJSP with sequencing flexibility. Due to the NP-hardness of the problem, a novel biomimicry hybrid bacterial foraging optimization algorithm (HBFOA) is developed, which is inspired by the behavior of E. colt bacteria in its search for food. The developed HBFOA search method is hybridized with simulated annealing (SA). Additionally, the algorithm has been enhanced by a local search method based on the manipulation of critical operations. Classical dispatching rules have been employed to create the initial swarm of HBFOA, and a new dispatching rule named minimum number of operations has been devised. The developed approach has been packaged in the form of a decision support system (DSS) developed on top of Microsoft Excel-a tool most small and mid-range enterprises (SME) use heavily for planning. A case study with local industry is presented to validate the proposed HBFOA and MILP. Additional numerical experiments using literature benchmarks are further used for validation. The results demonstrate that the HBFOA outperformed the classical dispatching rules and the best integer solution of MILP when minimizing the weighted tardiness and offered comparable results for the makespan instances.
Nowadays, the speech recognition applications can be found in several activities, and their existence as a field of study and research lasts for a long time. Although, many studies deal with different problems, in sec...
详细信息
Nowadays, the speech recognition applications can be found in several activities, and their existence as a field of study and research lasts for a long time. Although, many studies deal with different problems, in security-related areas, biometric identification, access to the Smartphone ... Etc. In automatic speech recognition (ASR) systems, hidden Markov models (HMMs) have widely used for modeling the temporal speech signal. In order to optimize HMM parameters (i.e., observation and transition probabilities), iterative algorithms commonly used such as Forward-Backward or Baum-Welch. In this article, we propose to use the bacterial foraging optimization algorithm (BFOA) to enhance HMM with Gaussian mixture densities. As a global optimizationalgorithm of current interest, BFOA has proven itself for distributed optimization and control. Our experimental results show that the proposed approach yields a significant improvement of the transcription accuracy at signal/noise ratios greater than 15 dB.
In modern era, the switched reluctance motors (SRM) are gaining attraction due to its inherent features such as robustness, low cost, simple, rugged structure, excellent fault tolerance and temperature withstanding ca...
详细信息
In modern era, the switched reluctance motors (SRM) are gaining attraction due to its inherent features such as robustness, low cost, simple, rugged structure, excellent fault tolerance and temperature withstanding capability. With these specialized advantages, the accurate and efficient energy analysis is still a challenging one since they operated at variable reluctance and oscillating excitation characteristics resulting in nonlinear characteristics. This paper focused on the energy improvement and performance analysis inclusive of smooth control in speed and minimized torque ripples of SRM by introducing the novel Bio-inspired methodology named bacterial foraging optimization algorithm (BFOA) for the selection of optimal parameters of the PID speed and current controllers. By minimizing the torque ripples, it increases the average torque which in turn increases the energy conversion. The performance of the SRM is measured in terms of speed, current, power and efficiency and BFOA efficiency has been verified with genetic algorithm (GA) and conventional PID controller using Euler forward approximation method. This paper discusses the modeling, controlling strategy using BFOA, GA and Euler forward approximation method and a comprehensive analysis of energy using optimized selection of controlling parameters. The performance evaluation objectives in this work, is to minimize Integral Square Error of both current and speed controller and also the reduction of torque ripples. The results obtained in this method are also compared with the Genetic algorithm and Euler forward approximation-based controllers. The proposed algorithm employs individual and social intelligences, which in turn search the responses between the local optima along with global optimums of the problem adaptively. The outmost dynamic response increased average torque and minimized current ripple can be obtained when the parameters of PID controllers are optimized using BFOA.
暂无评论