Artificial Neural Networks Combined with the Principal Component Analysis for Non-Fluent Speech Recognition

The presented paper introduces principal component analysis application for dimensionality reduction of variables describing speech signal and applicability of obtained results for the disturbed and fluent speech recognition process. A set of fluent speech signals and three speech disturbances—blocks before words starting with plosives, syllable repetitions, and sound-initial prolongations—was transformed using principal component analysis. The result was a model containing four principal components describing analysed utterances. Distances between standardised original variables and elements of the observation matrix in a new system of coordinates were calculated and then applied in the recognition process. As a classifying algorithm, the multilayer perceptron network was used. Achieved results were compared with outcomes from previous experiments where speech samples were parameterised with the Kohonen network application. The classifying network achieved overall accuracy at 76% (from 50% to 91%, depending on the dysfluency type).

Opportunities and Features of the Palynological Analysis Application on Various Types of Archaeological Sites

A wide variety of archaeological sites associated with various human activity has led to the emergence of a wide range of problems solved by archaeological palynology. On the example of the palynological materials accumulated in the Laboratory of Nature Sciences of the Institute of Archaeology of the Russian Academy of Sciences, the opportunities and features of the palynological analysis application are considered both on classical objects for Russian archaeopalynology (cultural layer, buried soils, defensive ramparts, burial mounds, etc.) and on non-traditional ones (latrines, vessels, funerary objects, ceramics, etc.). It is shown that the reconstruction of the natural environment, generally accepted for palynology, is mainly possible for the materials from long timed sites of shepherds in caves and rock shelters and cultural layers of sites, settlements, hillforts. Materials obtained from other objects (ancient and medieval arable lands, storage pits, latrines, the contents of ritual objects, vessels, and the gastrointestinal tract of the buried) give an idea of very local and short-term environmental conditions or events usually associated with economic and/or daily activities of a person, with his food, funerary rites and traditions. In this regard, the possibilities of the palynological method and the purposes will be different for each specific research. Recommendations for the sampling for palynological analysis are given for each specific case.

A Sensor-Based Drone for Pollutants Detection in Eco-Friendly Cities: Hardware Design and Data Analysis Application

The increase in produced waste is a symptom of inefficient resources usage, which should be better exploited as a resource for energy and materials. The air pollution generated by waste causes impacts felt by a large part of the population living in and around the main urban areas. This paper presents a mobile sensor node for monitoring air and noise pollution; indeed, the developed system is installed on an RC drone, quickly monitoring large areas. It relies on a Raspberry Pi Zero W board and a wide set of sensors (i.e., NO2, CO, NH3, CO2, VOCs, PM2.5, and PM10) to sample the environmental parameter at regular time intervals. A proper classification algorithm was developed to quantify the traffic level from the noise level (NL) acquired by the onboard microphone. Additionally, the drone is equipped with a camera and implements a visual recognition algorithm (Fast R-CNN) to detect waste fires and mark them by a GPS receiver. Furthermore, the firmware for managing the sensing unit operation was developed, as well as the power supply section. In particular, the node’s consumption was analysed in two use cases, and the battery capacity needed to power the designed device was sized. The onfield tests demonstrated the proper operation of the developed monitoring system. Finally, a cloud application was developed to remotely monitor the information acquired by the sensor-based drone and upload them on a remote database.

Application of thermal analysis in ferrous and nonferrous foundries

This paper is devoted to the memory of Professor Ljubomir Nedeljkovic (1933-2020), Head of the Department of Iron and Steel Metallurgy University of Belgrade, Serbia. Assessment of the melt quality is one of the most important casting process parameters, which allowed sound production of intricated cast parts. At the present time, various devices have been applied at foundry floors to control melt quality. Thermal analysis is one of them, widely used for melt quality control in ferrous and non-ferrous casting plants. During solidification, metal and alloys released latent heat, which magnitude is dependent on the type of phases that form during the solidification process. Plotting temperature versus time data during solidification provides useful information related to the actual solidification process. The applied technique is called thermal analysis, whereas the cooling curve is the name of such a plot. The main aim of this paper is to give a short overview of the present thermal analysis application in various foundries and to indicate the future potential use of this technique.

Genetic Diversity, QTL Mapping, and Marker-Assisted Selection Technology in Cotton (Gossypium spp.)

Cotton genetic resources contain diverse economically important traits that can be used widely in breeding approaches to create of high-yielding elite cultivars with superior fiber quality and adapted to biotic and abiotic stresses. Nevertheless, the creation of new cultivars using conventional breeding methods is limited by the cost and proved to be time consuming process, also requires a space to make field observations and measurements. Decoding genomes of cotton species greatly facilitated generating large-scale high-throughput DNA markers and identification of QTLs that allows confirmation of candidate genes, and use them in marker-assisted selection (MAS)-based breeding programs. With the advances of quantitative trait loci (QTL) mapping and genome-wide-association study approaches, DNA markers associated with valuable traits significantly accelerate breeding processes by replacing the selection with a phenotype to the selection at the DNA or gene level. In this review, we discuss the evolution and genetic diversity of cotton Gossypium genus, molecular markers and their types, genetic mapping and QTL analysis, application, and perspectives of MAS-based approaches in cotton breeding.