Training of Feed-Forward Neural Networks by Using Optimization Algorithms Based on Swarm-Intelligent for Maximum Power Point Tracking.

One of the most used artificial intelligence techniques for maximum power point tracking is artificial neural networks. In order to achieve successful results in maximum power point tracking, the training process of artificial neural networks is important. Metaheuristic algorithms are used extensively in the literature for neural network training. An important group of metaheuristic algorithms is swarm-intelligent-based optimization algorithms. In this study, feed-forward neural network training is carried out for maximum power point tracking by using 13 swarm-intelligent-based optimization algorithms. These algorithms are artificial bee colony, butterfly optimization, cuckoo search, chicken swarm optimization, dragonfly algorithm, firefly algorithm, grasshopper optimization algorithm, krill herd algorithm, particle swarm optimization, salp swarm algorithm, selfish herd optimizer, tunicate swarm algorithm, and tuna swarm optimization. Mean squared error is used as the error metric, and the performances of the algorithms in different network structures are evaluated. Considering the results, a success ranking score is obtained for each algorithm. The three most successful algorithms in both training and testing processes are the firefly algorithm, selfish herd optimizer, and grasshopper optimization algorithm, respectively. The training error values obtained with these algorithms are 4.5 × 10-4, 1.6 × 10-3, and 2.3 × 10-3, respectively. The test error values are 4.6 × 10-4, 1.6 × 10-3, and 2.4 × 10-3, respectively. With these algorithms, effective results have been achieved in a low number of evaluations. In addition to these three algorithms, other algorithms have also achieved mostly acceptable results. This shows that the related algorithms are generally successful ANFIS training algorithms for maximum power point tracking.

Thermal imaging of the pulp during residual adhesive removal.

OBJECTIVE: The aim of this study was to evaluate the temperature changes of the pulpal area during different adhesive clean-up procedures. MATERIALS AND METHODS: A total of 80 freshly extracted adult maxillary premolar teeth were divided into four groups. Adhesive clean-up was performed with 6- and 12-fluted tungsten carbide burs (TCB) using low- and high-speed handpieces with air or water cooling after bracket debonding. The temperature changes and cool down times were evaluated with a thermal camera. Paired t test, analysis of variance (ANOVA), and Student-Newman-Keuls multiple comparison analysis were used for statistical analysis of the data. RESULTS: All experimental groups, except the water cooling group, showed a significant temperature rise (p < 0.001) after residual adhesive removal. Only the 6-fluted TCB group with air cooling using a high-speed handpiece exceeded the critical 5.5 °C threshold value (5.91 ± 0.89 °C); this group also exhibited the longest cool down time to initial temperature (71.95 ± 13.68 s). The smallest temperature rise (0.48 ± 0.90 °C) and shortest cooling time value (11.90 ± 5.3 s) were measured in the 6-fluted TCB group with water cooling using a high-speed handpiece. CONCLUSION: Appropriate cooling procedures and fine tungsten carbide burs should be used during the removal of remnant adhesives after bracket debonding in order to prevent adverse pulpal reactions.

Infrared thermographic comparison of temperature increases on the root surface during dowel space preparations using circular versus oval fiber dowel systems.

PURPOSE: The purpose was to evaluate temperature increases during dowel space preparations with oval and circular fiber dowel systems. MATERIALS AND METHODS: This study included 42 single-rooted human mandibular premolars. Roots were scanned with cone-beam computerized tomography (CBCT) to determine the ovoid root canal morphology. Root canals were treated with Ni-Ti rotary instruments and obturated. A second CBCT was taken to determine the thinnest dentin thickness of each root. Roots were randomly divided into two groups (n = 21) according to the fiber dowel system used: group 1, circular fiber dowel system (D.T. Light-Post); group 2, oval fiber dowel system (Ellipson Post). Dowel spaces were prepared using a circular fiber dowel drill and a diamond-coated ultrasonic tip with an oval section under water cooling until 9 mm dowel spaces were obtained. Temperature changes were recorded from the thinnest root surfaces using a FLIR E60 thermal imaging camera. RESULTS: Temperature increases were significantly greater with the circular fiber dowel system than with the oval fiber dowel system (p < 0.05). CONCLUSIONS: Although both dowel systems generated high temperature increases on root surfaces, the relatively lower temperature increase associated with the use of oval fiber dowels in ovoid canals makes it preferable to the use of circular fiber dowels.