Current issue
No 3/2020, September

Heuristic Evaluation of the User Interface for a Semi-Autonomous Agricultural Robot Sprayer


This study presents the heuristic evaluation, as a usability inspection method for Human-Robot Interaction (HRI) systems. First, the methodology to engineer a semi-autonomous agricultural robot sprayer is presented, and then findings from heuristic usability evaluation studies that were carried out on a human-robot interface for a semi-autonomous agricultural vineyard robot sprayer. The following research-based heuristics for the design of robot teleoperation were used: Platform architecture and scalability, Error prevention and recovery, Visual design, Information presentation, Robot state awareness, Interaction effectiveness and efficiency, Robot environment/surroundings awareness, and Cognitive factors. In each evaluation study, usability problems were identified, and specific suggestions were documented for HRI usability improvement. In each design iteration, a smaller number of usability issues were identified.. Results of the final heuristic evaluation showed that the system is at a good level of usability and is expected to provide satisfactory services to its typical users.

 VIEW MORE  PDF (.pdf, 1.19 MB)

Analysis of Online Consumer Behavior - Design of CRISP-DM Process Model


The basis of the modern marketing of a business entity is to know the behavior of its customers. Advanced artificial intelligence methods, such as data mining and machine learning methods, penetrate data analysis. The application of these methods is most appropriate in the case of online sales of any goods in large quantities and various industries. They are very often used in the sale of electronics, PCs or clothes. However, it is also possible to apply them to the agricultural industry, not only in B2C, but also in B2B in the sale of seeds, agricultural products, or agricultural machinery. Appropriate combinations of offers and knowledge of customers can bring the selling entity higher profits or competitive advantages. The main goal of our study is to design a CRISP-DM process model that will enable small businesses to analyze online customers' behavior. To reach the main goal we perform a data analysis of the online sales data by using machine learning methods as clustering, decision tree and association rules mining. After evaluating the proposed model, we discuss its use of the proposed model in the field of internet sales in the agricultural sector.

 VIEW MORE  PDF (.pdf, 704.37 KB)

Household Demand for Fruits and Vegetables in Rural and Urban South-Western Nigeria


In spite of the enormous benefits of fruits and vegetables, studies have shown that their consumption in Nigeria is far below the recommended daily intake therefore, this study investigated the factors influencing the demand for fruits and vegetables among households in rural and urban South-western Nigeria. Data were sourced from 152 rural and 259 urban households, respectively with the aid of a semi-structured questionnaire and were analysed using descriptive statistics and the quadratic almost ideal demand system model. Household size and location, sex and years of education of household heads influenced the demand for fruits and vegetables. Both rural and urban households considered the demand for fruits and vegetables to be luxury goods. Rural households were more responsive to changes in own-prices of fruits and vegetables than their urban counterpart. Fruits and vegetables were “net substitutes” in the rural and “complements” in the urban.

 VIEW MORE  PDF (.pdf, 1.53 MB)

Segmentation of Bean-Plants Using Clustering Algorithms


In recent years laser scanning platforms have been proven to be a helpful tool for plants traits analysing in agricultural applications. Three-dimensional high throughput plant scanning platforms provide an opportunity to measure phenotypic traits which can be highly useful to plant breeders. But the measurement of phenotypic traits is still carried out with labor-intensive manual observations. Thanks to the computer vision techniques, these observations can be supported with effective and efficient plant phenotyping solutions. However, since the leaves and branches of some plant types overlap with other plants nearby after a certain period of time, it becomes challenging to obtain the phenotypical properties of a single plant. In this study, it is aimed to separate bean plants from each other by using common clustering algorithms and make them suitable for trait extractions. K-means, Hierarchical and Gaussian mixtures clustering algorithms were applied to segment overlapping beans. The experimental results show that K-means clustering is more robust and faster than the others.

 VIEW MORE  PDF (.pdf, 1.71 MB)

Prediction and Context Awareness in Agriculture: A Systematic Mapping


The advances in sensorial technology and its use in agriculture have been contributing to the acquisition and analysis of data regarding agricultural production. Studies propose the use of sensors to monitor production or even the use of cameras to obtain crop information, providing data, reminders, and alerts to farmers. Through the obtainment and analysis of these data, context awareness can be used to improve systems, mainly through the prediction techniques applied to agriculture. This article presents a systematic mapping of studies that use prediction and context awareness in agriculture. During the mapping, 10206 articles were initially identified and, after filtering by inclusion and exclusion criteria, 42 articles were selected. The results indicated that 35.7% (15/42) of the studies used one or more prediction techniques and 45.2% (19/42) used image processing through pictures of cameras to obtain information regarding planting. 23 sensors with different functionalities were found, those have been used in the collection of data for context formation in agriculture.

 VIEW MORE  PDF (.pdf, 667.82 KB)

Economic Aspects of Precision Agriculture Systems


The paper deals with an economic assessment of impacts of precision agriculture (PA) on crop production economy. Based on a questionnaire survey and a FADN agricultural product expense-to-revenue ratio survey, it analyses a set of agricultural businesses the structure of which essentially copies the composition of business forms in the Czech Republic’s agricultural sector. The economic assessment applies economic analysis methods based on cost calculations and a calculation formula that considers the commodity and species production structure. Based on an analysis of a number of scientific studies, it determines specific cost savings and makes a quantification of the effect of precision agriculture techniques on costs. In all the production areas, the greatest effect caused by application of precision agriculture techniques was quantified for winter wheat. Conversely, the lowest financial effects are shown in the analysed production areas for spring wheat. We also identified differences in the cost savings between spring and winter barley; the greater savings occur for winter barley. Financial effects in the form of reduced production costs were also found for other analysed crops cultivated by the businesses studied. The financial savings for the pea plant are almost comparable to those for winter barley. The greatest financial savings were achieved for sugar beet.

 VIEW MORE  PDF (.pdf, 494.52 KB)

Parametric Insurance as Innovative Development Factor of the Agricultural Sector of Economy


In the article a parallel between the classical and parametric scheme of agricultural risk insurance is conducted. The application aspects of parametric (index) schemes of insurance with emphasis on the use of weather index insurance products are examined, their advantages and disadvantages are considered. This research examined the applicability along with simple weather index insurance products combined, that can consider and put together a few parameters simultaneously and thus neutralize the impact of the whole weather risks at regional level. The authors demonstrated the feasibility of using the proposed combination of weather index (Ci) – a special indicator which characterize the impact of weather risk combitation intensity, measured by certain parameters (heat, cold → temperature; air humidification → relative humidity; drought → precipitation) on the grain maize yield in definite growth stages (flowering and grain filling). On the basis of research, the detail mechanism proposed by the authors of the combined weather index (Ci) in general, and on the example of concreate calculations, is performed in particular.

 VIEW MORE  PDF (.pdf, 2.84 MB)

Recent Evolution of Perennial Crop Farms: Evidence from Dak Lak Province, Vietnam


There is a great consensus about the crucial role of perennial crops in an agricultural economy of a country. The paper aims (1) to identify the differences in the costs and profits of perennial crops produced by two study groups, a group producing coffee (GpC) and a group producing pepper (GpP) over two crop years 2016/2017-2017/2018; (2) evaluate the evolution of the economic performance of each group during two years; and (3) examine factors influencing the farm profitability. By using the mixed data from a household survey conducted in three sub-regions of Dak Lak province, Vietnam, a financial verification is used to explore the economic incentives between two groups and a discriminant analysis is undertaken to classify the determinants of the farm profitability. The results perform that the GpC is generally lower input costs and economic benefits than the GpP. The decrease of economic indicators of the GpP during two years, meanwhile, is more significant than that of the GpC in the same period. In addition, the GpP is likely to invest more inputs, heavily use chemical cost, be more susceptible to pests and diseases, and the volatile market conditions in comparison to the GpC. Categorically, the variable cost and reduction rate in terms of value-added, net farm income (NFI), profit, labor productivity, and the ratio of NFI to family labor of the GpC have lower than those of the GpP, respectively, during two years. Furthermore, in similarly conditional practices, the perennial crop farms generate different returns depending on experience, training, other income, and gross outputs. The findings provide information for farmers to make accurate decision about coffee and pepper farms production as recommended by reducing the quantity of fertilizers, allocating resources and diversifying crop systems. Additionally, the empirical results also offer policymakers the farms sustainable development at local and national levels. Going forward, authors suggest these factors be considered in the future.

 VIEW MORE  PDF (.pdf, 802.4 KB)

Comparison of Fuzzy Multi-Criteria Decision-Making Methods to Rank Business Strategies and Marketing Resources


Given the growing competition in domestic and international agricultural product markets, choosing a business strategy compatible with requirements of marketing resources can guide agro-food firms to maintain and enhance competitive advantages. However, this is not as simple as it seems because the decision-making criteria expressed in a fuzzy manner and the relationship between them can be hierarchical or network-based. Therefore, the main goal of this study was to select the most suitable business strategy and to prioritize marketing resources for one of the major agro-food firms in Iran. To ensure the robustness of the results, both fuzzy analytic hierarchy process (AHP) and fuzzy analytic network process (ANP) were applied to prioritize business strategies and marketing resources. The results of both methods revealed that the differentiation strategy had the highest priority in terms of the experts' viewpoints. The results also showed that managerial and customer relationship capabilities were the most important criteria in selecting the differentiation strategy. According to the findings of the study, for the successful implementation of the differentiation strategy, company managers are recommended to take the following three main elements into huge consideration: financial conditions, paying attention to customer’s needs and requirements, and the introduction of new products and services.

 VIEW MORE  PDF (.pdf, 1.14 MB)

Productivity of Czech Milk Production in European Comparison


The aim of the paper is to evaluate the development and main characteristics of Czech milk production productivity and to compare Czech development with the situation in the European Union. From a methodological point of view, a parametric approach in the form of stochastic frontier analysis was applied, the input distance function was estimated, and total factor productivity was examined. The analysis used an unbalanced panel data set, which describes TF14-45 specialist milk production from 27 member states of the European Union in the period 2004–2016 collected in the FADN database. The results showed that in the Czech Republic, the average value of technical efficiency was 94.01% during the analysed time period. Compared to EU member states, this figure was above the EU-13 average (93.71%). Czech milk production in the analysed period and the milk production of almost all other EU countries was characterized by increasing returns to scale. Examination of total factor productivity (TFP) showed that the scale effect and technical efficiency change effect can be considered the main components of TFP changes in Czech milk production. However, the scale effect was more significant in EU-15 countries than the Czech milk sector.

 VIEW MORE  PDF (.pdf, 594.05 KB)