[Purpose] To evaluate the efficacy of our special rehabilitation method for patients with low back pain (LBP). [Subjects and Methods] All participants (n=33) received at least five individual 30-minute therapy sessions per week using the INFINITY method® and six group therapy sessions per week in a gymnasium and swimming pool, each lasting 30 minutes and including the INFINITY method®. The treatment lasted between four to seven weeks. Plantar function using a graphic method (computer plantography), graphical quantification of postural control during static standing (posturography), and pain were measured and evaluated before and after rehabilitation therapy. The INFINITY method® is a special rehabilitation method for patients with musculoskeletal problems. The method focuses on stabilization and strengthening of the trunk, dorsal and abdominal muscles, including the deep stabilization system which is closely linked with diaphragmatic breathing. It teaches the central nervous system to control muscles more precisely. [Results] Plantar functions, postural control in the upright stance and pain of LBP patients were significantly improved by 4−7 weeks of rehabilitation treatment with the INFINITY method®. There were significant differences in all measured dependent variables of the patients between before and after treatment. [Conclusion] Rehabilitation therapy with the INFINITY method® positively influences body stabilization and pain in patients with problems of the lumbar spine. This method presents a new improved approach (with enhanced effect) to rehabilitation therapy for LBP patients.

No abstract

No abstract

No abstract

In many industry and research areas, data mining is a crucial process. This paper presents an evolving structure of classifiers (random forest) where the trees are generated by hybrid method combining Ant Colony metaheuristics and Evolutionary computing technique. The method benefits from the stochastic process and population approach, which allows the algorithm to evolve more efficiently than each method alone. As the method is similar to random forest generation, it can be also used for feature selection. The paper also discusses the parameter estimation for the method. Tests on real data (UCI and real biomedical data) have been performed and evaluated. The average accuracy of the method over MIT-BIH database with normalized data and equalized classes is sensitivity 93.22 % and specificity 87.13 %.