Artificial neural networks for voice activity detection Technology

Currently, the direction of voice biometrics is actively developing, which includes two related tasks of recognizing the speaker by voice: the verification task, which consists in determining the speaker's personality, and the identification task, which is responsible for checking the belonging of the phonogram to a particular speaker. An open question remains related to improving the quality of the verification identification algorithms in real conditions and reducing the probability of error. In this work study Voice activity detection algorithm is proposed, which is a modification of the algorithm based on pitch statistics; VAD is investigated as a component of a speaker recognition system by voice, and therefore the main purpose of its work is to improve the quality of the system as a whole. On the example of the proposed modification of the VAD algorithm and the energy-based VAD algorithm, the analysis of the influence of the choice on the quality of the speaker recognition system is carried out.

ESTERCO OVINO AUMENTA A CAPACIDADE DE RETENÇÃO E MANUTENÇÃO DE ÁGUA NO SOLO DO CARIRI PARAIBANO

ESTERCO OVINO AUMENTA A CAPACIDADE DE RETENÇÃO E MANUTENÇÃO DE ÁGUA NO SOLO DO CARIRI PARAIBANO LUCYELLY DÂMELA ARAÚJO BORBOREMA1; PATRÍCIA DA SILVA COSTA2; PRISCYLLA MARQUES DE OLIVEIRA VIANA3; YANKA BEATRIZ GONÇALVES BATISTA4; MATHEUS CAVALCANTE DA SILVA5 E RENER LUCIANO DE SOUZA FERRAZ6 1. Unidade Acadêmica de Tecnologia do Desenvolvimento, Universidade Federal de Campina Grande, Rua Luiz Grande, S/N, Bairro Frei Damião, CEP 58540-000, Sumé, Paraíba, Brasil, [email protected]. 2 Unidade Acadêmica de Engenharia Agrícola, Universidade Federal de Campina Grande, Rua Aprígio Veloso, n° 882, Bairro Universitário, CEP 58428-830, Campina Grande, Paraíba, Brasil. [email protected]. 3 Departamento de Agroecologia e Agropecuária, Universidade Estadual da Paraíba, Sítio Imbaúba, S/N, Zona Rural, CEP 58117-000, Lagoa Seca, Paraíba, Brasil, [email protected]. 4 Unidade Acadêmica de Tecnologia do Desenvolvimento, Universidade Federal de Campina Grande, Rua Luiz Grande, S/N, Bairro Frei Damião, CEP 58540-000, Sumé, Paraíba, Brasil, [email protected]. 5 Unidade Acadêmica de Tecnologia do Desenvolvimento, Universidade Federal de Campina Grande, Rua Luiz Grande, S/N, Bairro Frei Damião, CEP 58540-000, Sumé, Paraíba, Brasil, [email protected]. 6 Unidade Acadêmica de Tecnologia do Desenvolvimento, Universidade Federal de Campina Grande, Rua Luiz Grande, S/N, Bairro Frei Damião, CEP 58540-000, Sumé, Paraíba, Brasil, [email protected]. 1 RESUMO A matéria orgânica do solo contribui para a sustentabilidade dos sistemas agrícolas, pois, influencia os atributos físicos, químicos e biológicos do solo, estabilizando a produtividade dos agroecossistemas. O teor de matéria orgânica no solo beneficia o aumento da capacidade de troca de cátions, assegurando os nutrientes no solo e reduzindo suas perdas por lixiviação. Nesse sentido, objetivou-se avaliar doses de esterco ovino para retenção e manutenção de água no solo na Microrregião do Cariri paraibano. O delineamento utilizado foi o inteiramente casualizado com seis doses de esterco ovino (0, 5, 10, 15, 20 e 25%, m/m) e quatro repetições. Foram realizadas avaliações de pesagem durante seis dias, a cada 24 h, para a determinação da porcentagem de água disponível em relação à massa seca do solo (m/m). Os dados foram submetidos à análise de variância ao nível de 5% de probabilidade de erro e as médias das doses de esterco foram submetidas a regressão polinomial. O esterco ovino aumenta a capacidade de retenção e manutenção da água no solo do Cariri paraibano, sendo uma alternativa para a atenuação dos problemas ocasionados pela perda de água por lixiviação e, por conseguinte, melhorando a capacidade produtiva do solo e vida dos produtores. Keywords: matéria orgânica, nutrientes no solo, status hídrico. BORBOREMA, L. D. A.; COSTA, P. S.; VIANA, P. M. O.; BATISTA, Y. B. G.; SILVA, M. C.; FERRAZ, R. L. S. SHEEP MANURE INCREASES THE WATER HOLDING AND MAINTENANCE CAPACITY OF SOIL IN THE CARIRI PARAIBANO REGION 2 ABSTRACT Soil organic matter contributes to the sustainability of agricultural systems, as it influences the physical, chemical and biological attributes of the soil, stabilizing the productivity of agroecosystems. The organic matter content in the soil benefits the increase of the cation exchange capacity, ensuring the nutrients in the soil and reducing its losses due to leaching. In this sense, the objective was to evaluate different doses of sheep manure for retention and maintenance of water in the soil in the Microregion of Cariri, in Paraíba state. The design used was completely randomized with six doses of sheep manure (0, 5, 10, 15, 20 and 25%, w/w) and four replications. Weighing evaluations were carried out for six days, every 24 h, to determine the percentage of available water in relation to the soil dry mass (w/w). Data were subjected to analysis of variance at a 5% probability of error and means of sheep manure doses were submitted to polynomial regression. Sheep manure increases the capacity of retaining and maintaining water in the soil of Cariri, in Paraíba state, being an alternative to alleviate the problems caused by the loss of water through leaching and, therefore, improving the productive capacity of the soil and the life of producers. Keywords: organic matter, soil nutrients, water status.

Software and technological complex of identification of sea vessels based on the use of radar space images Sentinel 1

The paper considers the problem of using images from SAR satellites for the identification of seagoing vessels. It describes the main functions of software and technological complex of the automated monitoring. The system is operated with utilizing space images of SAR satellites Sentinel 1A (B). The algorithmic part, which implements the detection on the sea surface the marks associated with ships, is described in details. To reduce the impact of speckle-noise, the image is pre-processed with the improved Lee-filter. Further processing lies in using an adaptive threshold algorithm that provides detection for each local background fragment of the image the unusually bright pixels, at the same time the algorithm provides a constant probability of error. By solving a nonlinear equation, for each position of the background window the algorithm finds the threshold brightness value and then all pixels above this value are considered vessels. In advance the evaluation of parameters of statistical distribution of pixels’ brightness is performed for each position of the background window. K-mean is used for such distribution. The selected bright pixels are combined into compact groups and their size and coordinates are being determined. The obtained results are compared with the data of the AIS, Automatic Identification System of ships, and the results are displayed on a cartographic basis.

Optimal nonlinear filtering of M-PSK signals against a background of harmonic interference with a random initial phase

Objectives. The widespread use of radio data transmission systems using signals with multiposition phase shift keying (MPSK) is due to their high noise immunity and the simplicity of constructing the transmitting and receiving parts of the equipment. The conducted studies have shown that the presence of non-fluctuation interference, in particular, harmonic interference, in the radio channel significantly reduces the noise immunity of receiving discrete information. The energy loss in this case, depending on the interference intensity, can range from fractions of dB to 10 db or more. Therefore, interference suppression is an important task for such radio systems. The aim of the work is to synthesize and analyze an algorithm for optimal nonlinear filtering of MPSK signals against a background of harmonic interference with a random initial phase.Methods. The provisions of the theory of optimal nonlinear signal filtering and methods of statistical radio engineering are used.Results. The synthesis and analysis of the algorithm of optimal nonlinear filtering of MPSK signals against the background of harmonic interference with a random initial phase are carried out. The synthesized receiver contains a discrete symbol evaluation unit, two phase-locked frequency circuits of reference generators that form evaluation copies of the signal and interference, and cross-links between them. Analytical expressions are obtained that allow calculating the dependences of the bit error probability on the signal-to-noise ratio and the interference intensity µ. It is established that uncompensated fluctuations of the initial phase of the useful signal have a greater effect on the receiver noise immunity than similar fluctuations of the phase of harmonic interference, especially with low positional signals.Conclusions. Comparison of the obtained results with the results obtained in the case when there are no harmonic interference compensation circuits shows that the use of the obtained phase filtering algorithms allows for almost complete suppression of harmonic interference. Thus, if µ = 0.5 and the probability of error is 10−2, the energy gain at M = 2 is about 2.5 dB, at M = 4 – about 6 dB, at M = 8 and M = 16 – at least 10 dB.

Can the financial performance of the micro, small, and medium-sized enterprise production sector in Medan be a signal in the use of a leanness strategy?

Background: Business actors need to take strategic steps to maintain and improve business performance. Studying and deepening the strategies used by micro, small, and medium-sized enterprises (MSMEs) to maintain their performance conditions are needed as a barometer of crisis resistance in the macroeconomic sector, especially those used by MSMEs in Medan, Indonesia. Thus, this research provides a real picture in the field of variables and indicators that affect the business strategy of MSMEs through the perspective of a lean approach. Methods: The population in this region was 466 business actors of MSMEs in Medan. A random stratified sampling strategy is used, and 169 businesses in the MSMEs production sector were obtained as samples, which has exceeded the standard achievement of 80 percent in detecting an R2 value of at least 0.10 (with a 5 percent probability of error). The research variables used consisted of one endogenous variable (use of a lean strategy), two exogenous variables (external lean practice and internal lean practice), and one mediating variable (financial performance). Seven hypotheses (inner models) were tested using structural equation modelling–partial least squares, nonparametric statistical data analysis techniques with mediation effects, assisted by Smart PLS 3.0. Results: Based on the path coefficient, internal lean practice predominantly influences the financial performance of MSMEs in Medan compared to external lean practice. Internal lean practice is the primary signal for identifying the degree of lean strategy practice in the MSMEs production sector in Medan city. Conclusion: These findings can be a map for practitioners, academics, and the government to improve the financial performance of MSMEs and assist them in their business strategies through internal business practices. Moreover, this study's impact can lead to an understanding of business strategies in operations that directly or indirectly affect the environment toward global warming and various environmental problems.

On the Non-Adaptive Zero-Error Capacity of the Discrete Memoryless Two-Way Channel

We study the problem of communicating over a discrete memoryless two-way channel using non-adaptive schemes, under a zero probability of error criterion. We derive single-letter inner and outer bounds for the zero-error capacity region, based on random coding, linear programming, linear codes, and the asymptotic spectrum of graphs. Among others, we provide a single-letter outer bound based on a combination of Shannon’s vanishing-error capacity region and a two-way analogue of the linear programming bound for point-to-point channels, which, in contrast to the one-way case, is generally better than both. Moreover, we establish an outer bound for the zero-error capacity region of a two-way channel via the asymptotic spectrum of graphs, and show that this bound can be achieved in certain cases.

Practical Nonparametric Sampling Strategies for Quantile-Based Ordinal Optimization

Given a finite number of stochastic systems, the goal of our problem is to dynamically allocate a finite sampling budget to maximize the probability of selecting the “best” system. Systems are encoded with the probability distributions that govern sample observations, which are unknown and only assumed to belong to a broad family of distributions that need not admit any parametric representation. The best system is defined as the one with the highest quantile value. The objective of maximizing the probability of selecting this best system is not analytically tractable. In lieu of that, we use the rate function for the probability of error relying on large deviations theory. Our point of departure is an algorithm that naively combines sequential estimation and myopic optimization. This algorithm is shown to be asymptotically optimal; however, it exhibits poor finite-time performance and does not lead itself to implementation in settings with a large number of systems. To address this, we propose practically implementable variants that retain the asymptotic performance of the former while dramatically improving its finite-time performance.

Разработка тренажерных установок для подготовки персонала нефтеперерабатывающих предприятий

In modern conditions of fierce competition in the energy market, the enterprises of the Russian Federation widely use new technologies, introduce modern equipment and automation systems. This leads to the increased requirements for the quality of management and maintenance of industrial objects, including oil refining facilities. When training the personnel of a hazardous production facility, the most important factor in assessing the results of training is the availability of not only theoretical knowledge, but also practical skills of work, including in emergency situations, which is difficult to learn in real production conditions. According to the number of studies, in the presence of practiced practical skills, the probability of error decreases significantly. Simulator training is one of the most efficient methods of practical training. Various versions are considered related to the simulators implemented on the computers and connected to the computer network; they simulate the workplace of specialists as much as possible. Integrated training systems are a set of interactive equipment and are designed to increase the level of fire and industrial safety of oil and gas facilities in the normal and emergency operating modes. The purpose of creating educational and training complexes is to conduct primary training of personnel of the enterprises for forming the managerial skills and an idea of the essence and features of the technological process. Thus, the future specialists can acquire skills in managing these processes in various situations. The substantiation and features of the use of quantitative assessments of the results of practical exercises and trainings for the specialists of oil refineries are given, as well as a method for calculating the direct assessment of the probable damage.

GC-MS Analysis of the Compositions and Antimicrobial Activities of Essential Oils From Five Species of Lamiaceae in Iran

Essential oils (EOs) separated from Lamiaceae species attract more attention due to their abundant use in the preservation of natural foods and pharmaceutics and have gained considerable interester in research and industrial. The aim of this study was to evaluate composition and antimicrobial activity of EOs obtained from five species Lamiaceae in Iran. After extraction of EOs by Clevenger, their composition was evaluated by gas chromatography-mass spectrometry (GC–MS). Antimicrobial properties were assayed by measuring inhibition zones, minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC). The results showed that the effects of species, on yield and predominant compounds amount of EOs of five species were significant with a probability of error of 1 %. The yield of oils were varied from ~ 0.02 to ~ 1.88%. About 66 components were identified by gas chromatography-mass spectrometry (GC-MS), and the dominant compounds were included thymol (67.71%), oleic acid (0.49–62.09%), (-)-caryophyllene oxide (0.41–24.81%), α-pinene (1.09–19.41%), 1,8-cineole (0.22–15.40%), palmitic acid (0.32–13.28%), (+)spathulenol (11.16%), and germacrene D (0.30-10.26%) in different species. The results of analysis of variance showed that there was a significant difference between the mean of the inhibition zone obtained treating the different microorganisms with the essential oil of five species (P ≤ 0.01). The highest inhibition zone belonged to TDEO (39.33 ± 0.58 and 25.00 ± 0.00 mm) against Gram-positive S. aureus and A. brasiliensis. The Gram-negative P. aeruginosa showed the lowest inhibitory resistance to HIEO, SIEO, and ROEO (with a MIC value of 31.25 µg/mL), which was very significant compared to rifampin. Therefore, EOs of five species have potential applications in the control of various bacteria and fungi and can be a natural alternative to some antibiotics.

Mineral Fertilization Increases Litterfall in Degraded Soils by Arenization

Young stands on sandy soils with low natural fertility are more dependent on chemical fertilization. The litterfall becomes the most important route for biogeochemical cycling in an ecosystem. Therefore, the aim of the study was to quantify the annual litterfall, evaluate the seasonality of deposition and verify the litterfall response under different amounts of fertilizers in a young eucalyptus stand implanted in soil degraded by arenization in southern Brazil. Litterfall was evaluated using litter traps with an area of 0.5 m². Fortnightly, over a year, collections and quantification of dry mass were performed. Each of the 5 fertilizer treatments received increasing amounts of nutrients. The litterfall had seasonal pattern, with larger quantities for the spring season, with statistical difference at a level of 5% probability of error from other seasons evaluated, marked by the increase in temperatures. The amount of litterfall, in descending order, followed the amount of nutrients applied in the treatments: T5 > T3 > T4 > T2 > T1. The annual litterfall ranged from 518 to 1326 kg ha-1 of the treatment that received natural phosphate (T1) and triple superphosphate (T5), respectively. This variation represents an increase of 156%. The increase in litterfall is associated with the amount of fertilizers.