This paper presents an implementation of the parallelization of genetic algorithms. Three models of parallelized genetic algorithms are presented, namely the Master-Slave genetic algorithm, the Coarse-Grained genetic algorithm, and the Fine-Grained genetic algorithm. Furthermore, these models are compared with the basic serial genetic algorithm model. Four modules, Multiprocessing, Celery, PyCSP, and Scalable Concurrent Operation in Python, were investigated among the many parallelization options in Python. The Scalable Concurrent Operation in Python was selected as the most favorable option, so the models were implemented using the Python programming language, RabbitMQ, and SCOOP. Based on the implementation results and testing performed, a comparison of the hardware utilization of each deployed model is provided. The results' implementation using SCOOP was investigated from three aspects. The first aspect was the parallelization and integration of the SCOOP module into the resulting Python module. The second was the communication within the genetic algorithm topology. The third aspect was the performance of the parallel genetic algorithm model depending on the hardware.

• Klíčová slova
• Coarse-Grained, Fine-Grained, Master–Slave, SCOOP, parallelized genetic algorithms,
• MeSH
• algoritmy * MeSH
• počítače * MeSH
• Publikační typ
• časopisecké články MeSH

In this paper, we propose an innovative Federated Learning-inspired evolutionary framework. Its main novelty is that this is the first time that an Evolutionary Algorithm is employed on its own to directly perform Federated Learning activity. A further novelty resides in the fact that, differently from the other Federated Learning frameworks in the literature, ours can efficiently deal at the same time with two relevant issues in Machine Learning, i.e., data privacy and interpretability of the solutions. Our framework consists of a master/slave approach in which each slave contains local data, protecting sensible private data, and exploits an evolutionary algorithm to generate prediction models. The master shares through the slaves the locally learned models that emerge on each slave. Sharing these local models results in global models. Being that data privacy and interpretability are very significant in the medical domain, the algorithm is tested to forecast future glucose values for diabetic patients by exploiting a Grammatical Evolution algorithm. The effectiveness of this knowledge-sharing process is assessed experimentally by comparing the proposed framework with another where no exchange of local models occurs. The results show that the performance of the proposed approach is better and demonstrate the validity of its sharing process for the emergence of local models for personal diabetes management, usable as efficient global models. When further subjects not involved in the learning process are considered, the models discovered by our framework show higher generalization capability than those achieved without knowledge sharing: the improvement provided by knowledge sharing is equal to about 3.03% for precision, 1.56% for recall, 3.17% for F1, and 1.56% for accuracy. Moreover, statistical analysis reveals the statistical superiority of model exchange with respect to the case of no exchange taking place.

• Klíčová slova
• diabetes, evolutionary algorithms, federated learning, interpretable machine learning,
• MeSH
• algoritmy * MeSH
• glukosa MeSH
• lidé MeSH
• soukromí MeSH
• strojové učení * MeSH
• znalosti MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• Názvy látek
• glukosa MeSH

At present the most widely used system of CAS is a vocally controlled manipulator of the laparoscope AESOP 3000 (Automated Endoscopic System for Optimal Positioning) which makes it possible to implement some operations without the assistance of another surgeon ("Solo-surgery"). Because of financial costs the so far little used equipment ZEUS or DA VINCI are already "master-slave" systems with several robot arms where the surgeon operates by means of manipulators in the controlling unit without direct contact with the patient. At the First Surgical Clinic, General Faculty Hospital and First Medical Faculty Charles Universitx the authors use the robot system AESOP 3000 since March 2000, in particular in laparoscopic gastric banding on account of obesity, in laparoscopic cholecystectomies, laparoscopic gastroenteroanastomoses and operations in the area if the hiatus. This system made it possible to reduce the number of assisting physicians. E.g. in gastric banding one assistant is sufficient, in laparoscopic cholecystectomy it is possible to operate only with a suture nurse. The application of AESOP is particularly useful in laparoscopic appendectomies and inguinal hernioplasties where it makes possible so-called "solo-surgery" or "one man surgery". No doubt, it is however necessary to have the possibility to call immediately another doctor to the operation theatre in case of necessary conversion of laparoscopy of laparotomy. The authors did not record any case of unwanted movement of the robot arm or another serious technical problem. As compared with a manually guided laparoscope during the use of AESOP the number of unwanted or inadequate shifts of the optical equipment or its angular rotation decreased considerably.

• MeSH
• chirurgie s pomocí počítače * MeSH
• laparoskopie * metody   MeSH
• lidé MeSH
• robotika * MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• anglický abstrakt MeSH
• časopisecké články MeSH

Dog. Specifically created to save its master's life. - (The dog is the ideal) Friend of man, (because it is his devoted slave) (source: Gustave Flaubert, Dictionnaire des Idées Reçues). But is man the best friend of the dog? This question is legitimate when we consider living situations to which modern domestic dogs are exposed. They often do not satisfy basic animal needs. In this narrative review, the author revisits the history of the dog's presence alongside humans, in the light of current knowledge. The modern dog (breed standards and their interests in canine research) and its breeding strategy, including extreme breeding, will then be given particular attention. Dysfunctional human psychological processes will be explored to make it possible to grasp why the breeding of the modern dog is undergoing such a transformation. Finally, based on these factual and conceptual insights, suggestions to improve canine welfare will be proposed. To be effective, all these must be assessed against real-world conditions.

• Klíčová slova
• canine welfare, dog-human relationship, genetic defect, selective breeding,
• Publikační typ
• časopisecké články MeSH
• přehledy MeSH