Solving truck-cargo matching for drop-and-pull transport with genetic algorithm based on demand-capacity fitness

Risk Assessment Method of Agricultural Management Investment Based on Genetic Neural Network

“…e population size can be set according to the actual situation, and the general value range is [20,200]. (3) Individual fitness calculation: Fitness is the standard for evaluating the quality of chromosome individuals in the population and the basis for selecting genetic operation [20][21][22]. In the specific application, the design of the fitness function should be combined with the requirements of solving the problem itself.…”

“…In formula (22), o k is the result vector of the output layer of the network, and d k is the expected output vector obtained through sample training. According to the principle of model combination, the target search for the optimal solution is to select the weight threshold with the smallest error square and E performance by training in the neural network in the evolutionary generation of the sample.…”

Fuzzy-logic Approach to Estimating the Fleet Efficiency of a Road Transport Company: A Case Study of Agricultural Products’ Deliveries in Kazakhstan

“…The directions of research in recent scientific publications in the field of choosing a vehicle models and fleet structure are the following:  considering the probabilistic components of the transport process [8,10,12,[15][16][17][18][19][20],  considering the complex impact of technical and operational indicators [7,8,12,[21][22][23][24][25][26][27],  optimizing of environmental [9,28,29], economic [7,11,18,22,19,30] and social impacts, as well as a combination of these parameters [13,[31][32][33][34],  determining and optimizing of truck loading schedules [4,8,10,16,35,36],  considering the energy efficiency of freight transportation [21,24,37],  minimizing the size of the vehicles fleet [17,20],  ensuring the tractive effort reserves [32],  considering the trajectory of trucks according to the global positio...…”

“…The presence in the considered works of many variable parameters and the given formalization of the conditions for conducting research do not allow qualitative analysis of the results obtained and the development of recommendations that allow using any of the proposed methods as a universal one for choosing the optimal (rational) qualitative and quantitative vehicle models for transportation of the agro-industrial products in the conditions of Kazakhstani market. The above statement is also based on the fact that genetic algorithms and their modifications [1,4,10,11,[15][16][17]29], which are characterized by poor scalability to the complexity of the problem being solved, were often used to solve the optimization problems formulated in the listed above works. As other methods, the following approaches were used: hybrid Pareto optimal approaches [31], binary integer programming under uncertainty [8], fuzzy programming [12], generalized disjunctive programming [35], fuzzy-tuned models [43], and multiperiod multiplicative analysis [37], recursive logic modeling [38], binary probit and logit models [2], discrete continuum econometric models [18], agent-based modeling [32], and discrete event simulation modeling [6,9].…”

An Optimized Method for Accounting Information in Logistic Systems

“…The development of logistics information platform, especially after the active sharing economy, has attracted many scholars to carry out related research, but its research still focuses on the construction technology of logistics information platform [16], system structure [17,18] and application mode [19,20]. Although research on its operation has gradually emerged in recent years, such as the emergence of pricing [21] and auction mechanisms [22], especially business matching based on logistics information platforms, and discovery algorithms (such as matching) [23][24][25], but few people are involved in the research on response after logistics business discovery.…”