Research On The Scheduling Problems Of The Immunoassay Equipment Based On Swarm Intelligence Algorithm

As the improvement of modern medical science, immunoassay equipment is widely used in the process of medical testing. The research of optimal problem for automatic immunoassay equipment has become one of the research hotspots. Replacing manual testing with automatic equipment can liberate productive forces, avoid subjective errors and improve detection accuracy. The key problems for developing an automatic immunoassay equipment contain some parts as follows: software development, hardware development and scheduling optimal problem for detection process. Aiming at solving the scheduling optimal problem in detection process, two kinds of swarm intelligence algorithms are proposed in this article. A reasonable scheduling scheme could improve the detection efficiency. The main contents are as follows:(1) The development of immunoassay equipment and the scheduling problem are analyzed in detail. The reasonable scheduling scheme is important and necessary to save the cost of the detection and to improve the efficiency and accuracy of the equipment.(2) The constraints of the scheduling problem are analyzed according to the characteristics of the detection process, such as: reentrancy, flexibility, continuity, arms automatic composition and so on. The scheduling problem of the immunoassay equipment is summarized into a class of job-shop scheduling problem with special constraints. The mathematical model is established according to the constraints above.(3) The immune genetic algorithm is proposed to get optimal scheduling scheme in detection process. In this algorithm, the discrete encoding is used to construct the solution of scheduling problem. The crossover and mutation operator are designed and the vaccination operation based on the best antibody is proposed. The evaluation function is designed according to the antibody concentration. Then, the roulette operator is applied into selecting antibodies and suppressing the concentration of antibodies. Finally, the algorithm is tested by a series of examples. The simulation results show that the proposed algorithm is reasonable for solving the scheduling optimal problem of immunoassay equipment.(4) An improved teaching-learning-based optimization algorithm(TLBO-DL) is proposed. Aiming at the weak local search ability in existing TLBO, and considering that the learner should learn knowledge not only from the better learners, but also from itself, a novel differential self-learning operator is designed. The learning ability of learner is evaluated by its optimal and its learning times are adaptively calculated according to its learning ability. The learners with higher learning ability have more chance to learn by themselves. Finally, the proposed method is applied into solving the scheduling optimal problem. The experimental results show the effectiveness of the algorithm while solving the scheduling optimal problem. Both accuracy and robustness of the algorithm have been improved further.(5) As it takes a long time to detect the samples on the limited key devices which are always overloaded. In order to reduce the load of each key device, another object function has been considered. And then the scheduling problem become a kind of multi objective optimization problem. Based on the Pareto method, the multi objective optimization problem is solved by the IGA and the improved TLBO. The load of the key equipment is analyzed and it shows a balanced load on the key devices.