A Reward Population-Based Differential Genetic Harmony Search Algorithm

To overcome the shortcomings of the harmony search algorithm, such as its slow convergence rate and poor global search ability, a reward population-based differential genetic harmony search algorithm is proposed. In this algorithm, a population is divided into four ordinary sub-populations and one reward sub-population, for each of which the evolution strategy of the differential genetic harmony search is used. After the evolution, the population with the optimal average fitness is combined with the reward population to produce a new reward population. During an experiment, tests were conducted first on determining the value of the harmony memory size (HMS) and the harmony memory consideration rate (HMCR), followed by an analysis of the effect of their values on the performance of the proposed algorithm. Then, six benchmark functions were selected for the experiment, and a comparison was made on the calculation results of the standard harmony memory search algorithm, reward population harmony search algorithm, differential genetic harmony algorithm, and reward population-based differential genetic harmony search algorithm. The result suggests that the reward population-based differential genetic harmony search algorithm has the merits of a strong global search ability, high solving accuracy, and satisfactory stability.

Reinforcement Learning-Based Multihop Relaying: A Decentralized Q-Learning Approach

Conventional optimization-based relay selection for multihop networks cannot resolve the conflict between performance and cost. The optimal selection policy is centralized and requires local channel state information (CSI) of all hops, leading to high computational complexity and signaling overhead. Other optimization-based decentralized policies cause non-negligible performance loss. In this paper, we exploit the benefits of reinforcement learning in relay selection for multihop clustered networks and aim to achieve high performance with limited costs. Multihop relay selection problem is modeled as Markov decision process (MDP) and solved by a decentralized Q-learning scheme with rectified update function. Simulation results show that this scheme achieves near-optimal average end-to-end (E2E) rate. Cost analysis reveals that it also reduces computation complexity and signaling overhead compared with the optimal scheme.

A Fuzzy Production Inventory Model for Deteriorating Items with Shortages

In this paper we have developed a supply chain production inventory model for deteriorating items with shortage under Fuzzy environment. The formulae for the optimal average system cost, stock level, backlog level and production cycle time are derived when the deterioration rate is very small. In reality it is seen that we cannot define all parameters precisely due to imprecision or uncertainty in the environment. So, we have defined the inventory parameter deterioration rate as triangular fuzzy numbers. The signed distance method and graded mean integration method have been used for defuzzification. Numerical examples are taken to illustrate the procedure of finding the optimal total inventory cost, stock level and backlog level. Sensitivity analysis is carried out to demonstrate the effects of changing parameter values on the optimal solution of the system.

A Machine Learning Approach for Improving the Movement of Humanoid NAO’s Gaits

A humanoid robot’s development requires an incredible combination of interdisciplinary work from engineering to mathematics, software, and machine learning. NAO is a humanoid bipedal robot designed to participate in football competitions against humans by 2050, and speed is crucial for football sports. Therefore, the focus of the paper is on improving NAO speed. This paper is aimed at testing the hypothesis of whether the humanoid NAO walking speed can be improved without changing its physical configuration. The applied research method compares three classification techniques: artificial neural network (ANN), Naïve Bayes, and decision tree to measure and predict NAO’s best walking speed, then select the best method, and enhance it to find the optimal average velocity speed. According to Aldebaran documentation, the real NAO’s robot default walking speed is 9.52 cm/s. The proposed work was initiated by studying NAO hardware platform limitations and selecting Nao’s gait 12 parameters to measure the accuracy metrics implemented in the three classification models design. Five experiments were designed to model and trace the changes for the 12 parameters. The preliminary NAO’s walking datasets open-source available at GitHub, the NAL, and RoboCup datasheets are implemented. All generated gaits’ parameters for both legs and feet in the experiments were recorded using the Choregraphe software. This dataset was divided into 30% for training and 70% for testing each model. The recorded gaits’ parameters were then fed to the three classification models to measure and predict NAO’s walking best speed. After 500 training cycles for the Naïve Bayes, the decision tree, and ANN, the RapidMiner scored 48.20%, 49.87%, and 55.12%, walking metric speed rate, respectively. Next, the emphasis was on enhancing the ANN model to reach the optimal average velocity walking speed for the real NAO. With 12 attributes, the maximum accuracy metric rate of 65.31% was reached with only four hidden layers in 500 training cycles with a 0.5 learning rate for the best walking learning process, and the ANN model predicted the optimal average velocity speed of 51.08% without stiffness: V 1 = 22.62 cm / s , V 2 = 40 cm / s , and V = 30 cm / s . Thus, the tested hypothesis holds with the ANN model scoring the highest accuracy rate for predicting NAO’s robot walking state speed by taking both legs to gauge joint 12 parameter values.

ESTIMATION OF VEHICLE OPERATING TIME TAKING INTO ACCOUNT THE INFLUENCE OF A NUMBER OF FACTORS

Modern vehicles operated on the railways of Ukraine have almost exhausted or exceeded their resource. The overuse of financial and material resources for their maintenance continues. The standard service life of vehicles was calculated on stable economic conditions of use of vehicles and their timely updating in process of aging. The service life of modern vehicles is determined by the influence of many factors, the disregard of which can lead to significant costs, even in compliance with the standard service life. For railway transport, these factors need modern clarification, as in operation their service life often exceeds the standard or, as for intermodal transport, the service life does not have a strict justification. Accordingly, the article analyzes the issues of assessing the impact on the service life of vehicles of the components of the cost of its maintenance and average daily mileage. It is shown that, firstly, the definition of the service life of vehicles must be linked to the cost of vehicle development, its creation, testing and production, the cost of operation and storage, as well as additional costs, and secondly , with the optimal average daily mileage, at which all the costs are minimal.

Зависимость компоненты космического луча на фоне поверхности атмосферы от солнечной магнитной активности

Using Geant4 toolkit the changes of the flux density and of the dose rates of the secondary cosmic radiation at the heights up to 50 m from the land surface (at a depth of atmosphere about 1030 g/cm²) and depending on solar magnetic activity were estimated. For changes of Wolf’s number (sunspots) in the range of 0 — 200 the flux density of reflected from air and the soil g- and b- particles changes from 5.7 to 7 and 0.10 – 0.13 m-²s-¹ respectively, for energy from 0 keV to several units of GeV in the ground atmosphere on one meter from the earth. These estimates are much lower than those estimates, for radiation created by the soil and atmospheric radionuclides, which had been received earlier. In comparison with a contribution of radionuclides of the soil of flux density of secondary cosmic radiation about 0.01% and 0.1%, for gamma and beta radiation respectively. The received assessment of the dose rate transferred by secondary cosmic radiation about 0.7% from rate of the formed by soil’s radionuclides. In addition, an assessment of change in characteristics of secondary cosmic radiation depending on the level of solar magnetic activity presented in work. It is found that change of radiometric and dosimetric characteristics of secondary cosmic radiation depending on solar magnetic activity can be over 40%. It well repeats the changes of a dose found during a transcontinental flight. We found that the optimal average energy of spectrum of primary protons is 2.7 GeV. We can apply this feature to standards to find the most intensive periods of a secondary space gamma radiation and to use them in the experimental data, without involving the use of the Geant4. We have not found any significant contribution of secondary cosmic radiation reflected from the earth’s surface. This allows us to refuse from taking into account the soil layer in the model. С помощью инструментария Geant4 было произведено моделирование плотности потока и мощности дозы вторичного космического излучения на высотах до 50 м от поверхности земли (на глубине атмосферы около 1030 г/см²) и оценена их зависимость от солнечной магнитной активности. Для чисел Вольфа (количества пятен) в диапазоне от 0 до 200, плотность потока отраженных от воздуха и почвы g- и b-частиц изменялась от 5.7 до 7 и 0.10 — 0.13 м-²с-¹ соответственно для энергии от 0 кэВ до нескольких единиц ГэВ в приземной атмосфере на расстоянии одного метра от земли. Эти оценки намного ниже полученных ранее оценок для излучения, создаваемого почвенными и атмосферными радионуклидами. В сравнении с вкладом радионуклидов почвы в плотность потока, вклад вторичного космического излучения составляет около 0.01% и 0.1% для гамма- и бета-излучения соответственно. Полученная оценка мощности дозы, передаваемой вторичным космическим излучением, составляет около 0.7% от мощности дозы от радионуклидов из почвы. Кроме того, в работе представлена оценка изменения характеристик вторичного космического излучения в зависимости от уровня солнечной магнитной активности. Установлено, что изменение радиометрических и дозиметрических характеристик вторичного космического излучения в зависимости от солнечной магнитной активности может превышать 40%. Полученные результаты позволяют отказаться от учета слоя почвы в представленной модели.

Influence of hydrothermal conditions on the duration of the phenophase of common beans at different sowing dates in the forest-steppe conditions of the Ob region

The influence of hydrothermal conditions on the duration of phaseolus vulgaris L. phenophases of the grain direction at different sowing dates in the forest-steppe conditions of the Ob region was studied. The research was carried out on the experimental field of the training and production farm «Sad Michurintsev» at the Novosibirsk State Agrarian University. The objects of the study were the Rubin variety and the promising variety Krasno-pestriy. The structure of the growing season was studied and the samples were assessed by the duration of individual phenological phases. The influence of hydrothermal conditions on the change in the duration of the «sowing-emergence» interphase period was established at different sowing periods (up to 8 days) and the «seedlings-flowering» and «flowering-biological ripeness’ periods (up to 4 days). A one-way analysis of variance was carried out with a confidence interval of 5%. The optimal average sum of active temperatures for the passage of the main phenological phases «sowing-germination», «seedling-flowering» and «flowering-biological ripeness’ has been established: in Rubin it is 244, 518 and 709оС, and Krasno-pestriy is 241, 564 and 760оС, respectively. A relationship between the duration of the growing season and the average daily temperature (–0.90), the sum of temperatures (0.96), the duration of the growing season and the sum of precipitation (0.90) was revealed. The difference in precipitation of growing seasons at different sowing dates is insignificant and ranges from 120 to 131 mm. According to the results of the study, the recommended sowing time for the main groups of beans ripeness in the foreststeppe conditions of the Ob region is the second half of May.