Next Article in Journal
Powering the Future: Progress and Hurdles in Developing Proton Exchange Membrane Fuel Cell Components to Achieve Department of Energy Goals—A Systematic Review
Previous Article in Journal
Geographical Influences on Job–Housing Balance: A Study of Coastal Urban Areas in Boston
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sustainability
Volume 15
Issue 22
10.3390/su152215922
sustainability-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

An Approach to Assessing the State of Organic Waste Generation in Community Households Based on Associative Learning

by
Inna Tryhuba
1,
Taras Hutsol
2,3,*,
Anatoliy Tryhuba
1,
Agata Cieszewska
4,
Nataliia Kovalenko
5,
Krzysztof Mudryk
6,7,
Szymon Glowacki
8,*,
Andrzej Bryś
8,
Weronika Tulej
8 and
Mariusz Sojak
8
1
Department of Information Technologies, Lviv National Environmental University, 80-381 Dublyany, Ukraine
2
Department of Mechanics and Agroecosystems Engineering, Polissia National University, 10-008 Zhytomyr, Ukraine
3
Department of Machine Use in Agriculture, Dmytro Motornyi Tavria State Agrotechnological University, Zhukovskyi Str., 66, 69-002 Zaporizhzhia, Ukraine
4
Department of Landscape Architecture, Warsaw University of Life Sciences, Nowoursynowska 159, 02-787 Warsaw, Poland
5
Department of Administrative Management and Foreign Economic Activity, Faculty of Agrarian Management, National University of Life and Environmental Sciences of Ukraine, Heroiv Oborony, 11, 03-041 Kyiv, Ukraine
6
Faculty of Production and Power Engineering, University of Agriculture in Kraków, Balicka 116B, 30-149 Kraków, Poland
7
Ukrainian University in Europe–Foundation, Balicka 116, 30-149 Kraków, Poland
8
Department of Fundamentals of Engineering and Power Engineering, Institute of Mechanical Engineering, Warsaw University of Life Sciences (SGGW), 02-787 Warsaw, Poland
*
Authors to whom correspondence should be addressed.
Sustainability 2023, 15(22), 15922; https://doi.org/10.3390/su152215922
Submission received: 26 September 2023 / Revised: 30 October 2023 / Accepted: 10 November 2023 / Published: 14 November 2023
Browse Figures
Versions Notes

Abstract

:
The purpose of this work is to substantiate the approach to assessing the state of organic waste generation by households of a given community, which is based on passive production observations and intellectual analysis of statistical data, which ensures consideration of the factors and features of organic waste generation, as well as the development of qualitative models for forecasting their receipt. To achieve the goal, the following tasks were solved: the analysis of the state of organic waste generation by households in the EU countries was performed; an approach to assessing the state of organic waste generation by households of a given community is proposed; based on the use of the proposed approach, and models for assessing the state of organic waste generation of households in a given community were substantiated. The hypothesis of the study is to substantiate and use an approach to assessing the generation of organic waste by households in individual communities, based on the method of association learning and search for association rules, which will identify factors that have a significant impact on the volume of organic waste generated by households, the consideration of which will improve the accuracy of forecasting models and improve the quality of management of the processes of collection and processing of this waste in communities. The research methodology used allows for the use of data mining, probability theory, mathematical statistics, machine learning technology, and the Associative Rule Learning (ARL) method. Based on the use of a reasonable algorithm, they identify key trends and relationships between the factors of organic waste generation in communities in different countries, which is the basis for creating accurate models for predicting the volume of collection and processing of this waste in communities. The study found that the largest number of households produced organic waste per capita in the range of 0.14–0.25 kg/person. At the same time, most households have from two to four residents and are located on the adjoining territory from 350 m2 to 680 m2. Based on the method of learning associative rules, it was found that there are no close correlations between individual factors that determine the daily volume of organic waste generation by households per capita. The highest correlation coefficient between the type of housing and the income level of household residents is 0.13. The number of residents and the occupied area of the adjacent territory have the greatest impact on the daily volume of organic waste generated by households per capita. The substantiated associative rules of relationships, as well as the diagrams of relationships between factors, have helped to identify those factors that have the greatest impact on the volume of organic waste generation. They are the basis for creating accurate models for predicting the volume of collection and planning the processing of this waste in communities. Based on the proposed approach, Python 3.9 software was developed. It makes it possible to quickly carry out calculations and perform a quantitative assessment of the state of organic waste generation by households of a given community according to the specified rules of association between the volumes of organic waste generation and their factors. The results of the study are the basis for the further development of models for accurate forecasting of the collection and planning of the processing of organic waste from households in communities.

1. Introduction

Solving the problem of energy and environmental security is a priority task for many countries of the world. The mentioned problem is quite relevant for the EU countries, which are looking for ways for energy independence and are strengthening environmental requirements for methods of obtaining energy and fuel [1,2,3,4]. This leads to the emergence of a set of scientific and applied problems in various directions of circular production of environmentally clean types of energy from various types of raw materials. There are separate tasks that relate to increasing the energy independence and ecological functioning of households thanks to the circular use of organic waste [5,6,7]. The amount of organic waste generation is influenced by a number of specific factors, which requires the search for relationships between them in order to solve the problems of developing qualitative models for forecasting and classifying the generation of organic waste by households for the production of ecologically clean energy.
Based on the analysis of the state of use of organic waste by households of the world, it can be said that it differs significantly for individual countries with different levels of development [8,9,10,11]. For the production of compost or biogas, mainly organic household waste is used, such as food scraps, leaves, branches and other remains of plants and animals [12,13,14,15].
In countries with a high level of development, such as the USA, Canada and some Western European countries, the use of organic waste for the production of compost and biogas is quite common [16,17,18,19,20]. These countries have developed infrastructure for the collection and processing of organic waste, as well as initiatives aimed at reducing the amount of waste. In less developed countries, such as Africa and Southeast Asia, the use of organic waste for compost and biogas production is less common. Among them are countries where organic waste is simply thrown into the street or into rivers, which leads to environmental pollution and the spread of various diseases.
In general, the use of household organic waste is an important component of sustainable development and environmental protection of individual countries. To reduce the volume of organic waste and its effective use, it is necessary to establish cooperation between the government, business and citizens. However, there is a need for research to quantify the generation of household organic waste in individual settlements. This is the basis for the creation of qualitative models for forecasting the arrival of organic raw materials, the results of which provide justification for the configuration of systems for collecting and processing organic waste of households in individual communities.
The scientific novelty of the research lies in the development and substantiation of an approach to assessing the state of organic waste generation by community households based on passive observations, intellectual analysis of statistical data, and associative learning. This approach allows taking into account the factors and features of organic waste generation. At the same time, for the first time, associative learning was applied, which allows identifying of factors that have a significant impact on the volume of organic waste generation by households, and therefore searching for association rules that improve the accuracy of forecasting models and the quality of management of the processes of collection and processing of this waste in communities.
In our research, for the first time, we have developed an approach to assessing the state of organic waste generation by community households, which provides identification of important factors that make it possible to assess the peculiarities of organic waste generation in community households. The developed approach allows for a more accurate assessment of the volume of organic waste generation, which is an important prerequisite for improving the efficiency of recycling of this waste in communities.

2. Analysis of the Literature Data and Problem Statement

Recent publications on the use of organic waste for energy production demonstrate that this direction of energy and environmental security of territories is becoming more and more popular in many countries of the world [2,21,22]. The use of organic waste for energy production can help reduce environmental pollution and reduce dependence on unsustainable energy sources such as oil and gas [6,17,23,24,25,26,27,28,29]. Organic waste is a significant source of renewable energy, and its use can help reduce pollution and dependence on fossil fuels.
Recent studies and publications show a growing interest in the use of organic waste for energy production, in particular biogas and biofuels [30,31,32,33]. In these works, the potential of using organic waste for energy production in Europe is determined using geospatial analysis. Research shows that there is significant potential for the use of organic waste for energy production in the European Union, in particular from landfills, the economy, and the food industry [34].
The scientists in works [3,11,35,36,37,38] use various approaches concerning various aspects of using organic waste for energy production. Their obtained results can be useful for researching the effectiveness and economic feasibility of using organic waste and its impact on the environment. The research results obtained in the above-mentioned scientific papers can be useful for assessing the efficiency, economic feasibility and environmental impact.
Based on the results of research presented in scientific works [14,20,39], it can be stated that the use of organic waste for energy production is an effective and economical way of energy production. With the help of appropriate technologies, organic waste can be turned into biofuel, gas or electricity. Works [3,6,17] present the results of research on the use of organic waste for energy production, which will help reduce greenhouse gas emissions and reduce environmental pollution. In addition, the authors note that using this waste can reduce landfill maintenance costs and reduce energy costs for urban and rural communities. Overall, these publications confirm that the use of organic waste for energy production is economically and environmentally feasible.
One of the most discussed studies in recent years is the use of methane, which is formed during the decomposition of organic waste, for the production of electricity [4]. This technology, known as biogas production, is increasingly used in the agricultural sector and food production.
Scientific studies that are directly devoted to solving the problems of organic waste generation of households in a given community using various methods and algorithms deserve attention. They are presented in the works of Zorpas, A. A., Lasaridi, K., Voukkali, I. [5], Ozawa, S., Takai, K. [11], Bravi, M., Girotto, F. [14], Shahzad, K., Ehsan, A., Nawaz, A., Irshad, M. [36], and others. Works [40,41,42,43,44,45] cover various aspects of household organic waste issues, such as waste composition, their biological treatment, waste management in various urban and rural settlements, as well as public perception of the problem of their collection and processing.
However, the authors of the above-mentioned scientific works did not pay attention to the rather urgent tasks of assessing the state of organic waste generation of households in a given community, taking into account their characteristics. In addition, they do not provide an assessment of the unevenness of the state of organic waste generation of households in a given community based on the use of machine learning technologies. It is known [46,47,48,49,50,51] that the use of modern machine learning algorithms makes it possible to evaluate the relationships between factors that determine the effectiveness of processes in various spheres of society. At the same time, the substantiation of models, based on the use of methods of intellectual analysis of statistical data, makes it possible to substantiate the trends of changes in individual indicators of the generation and use of household organic waste and perform their qualitative forecasting. This is the basis of an adequate quantitative assessment of the state of organic waste generation by households of a given community.
Many studies have been conducted on the use of organic waste for energy production, but there is little research on the specific problems of estimating and forecasting organic waste generation at the community level. Existing methods for estimating organic waste generation at the community level are imprecise, and do not take into account all relevant factors, which makes it difficult to plan and implement effective waste management systems.
Thus, there is an important gap in the literature, as accurate estimates of household organic waste production in communities are the basis for the quality planning and implementation of effective waste management systems. Our study proposes a new approach to assessing the state of organic waste generation by community households based on associative learning. This approach takes into account the factors and characteristics of organic waste generation and allows for the development of high-quality models for predicting organic waste generation.
The purpose of the paper is to substantiate an approach to assessing the state of organic waste generation by households in a particular community, based on passive production observations, intellectual analysis of statistical data, and associative learning, which ensures the identification and consideration of important factors and features of organic waste generation, as well as the development of high-quality models for predicting their generation.
To achieve the goal, the following tasks should be solved:
-
Propose an approach to assessing the state of organic waste generation of households in a given community;
-
Based on the use of the proposed approach, justify models for assessing the state of organic waste generation of households in a given community.

3. An Approach to Assessing the State of Organic Waste Generation of Households in a Given Community

Assessment of the state of organic waste generation of households in a certain community begins with the collection of data on the generation of organic waste in the given territory (Figure 1). The following methods can be used to collect data on the generation of organic waste in a certain area:
(1)
Analysis of statistical data. This involves the study of statistical data on the generation of organic waste in a certain area. This method ensures the collection of data on the amount and composition of organic waste generated in local households. But most communities do not have such data, requiring the use of other methods.
(2)
Carrying out passive observations. Thanks to this method, it is possible to investigate the amount and composition of organic waste in a certain area by inspecting garbage containers and landfills, paying special attention to the content of organic waste. This method can only be used in places of collection and processing of organic waste.
(3)
Survey of the population of certain areas. With this data mining method, it is possible to survey the population of a certain area to determine the amount and composition of organic waste they generate in their households.
(4)
Study of reporting documentation of utility companies. This method is less accurate since, on its basis, it is possible to study documentation and reports on the production and disposal of organic waste in local enterprises and organizations.
Sustainability 15 15922 g001
Figure 1. Algorithm of the approach to assessing the state of organic waste generation by households of a given community.
Figure 1. Algorithm of the approach to assessing the state of organic waste generation by households of a given community.
Sustainability 15 15922 g001
The use of modern information technologies. In particular, this applies to the use of Internet of Things and machine learning technologies. Based on their use, it is possible to measure the content of organic waste in garbage containers of individual settlements using sensor devices and data collection systems. The received data can be processed using machine learning technologies.
Depending on the availability of resources and the purpose of the study, one or more methods can be used to collect data on the generation of household organic waste in a given area [52,53,54,55,56,57].
The next stage involves the intelligent analysis of data on the generation of organic waste in the given territory. It can help to understand what factors influence the amount of organic waste that is generated in households, and how it can be used for circular production of clean energy. An important component of this stage is the analysis of influencing factors on the amount of organic waste generated by households in a given territory of the community (Figure 2).
There are many factors that affect the amount of organic waste generated by households in a certain community area [43]. Among them, the most important factors are the type of settlement and households, the area of the territory of households, the number of household residents, the income level of household residents, etc. [4,30,43,53]. For example, the number of household residents or the number of families with children affects the volume of organic waste generation. An increase in the income level of household residents leads to an increase in the amount and types of food consumption which, in turn, leads to an increase in the amount of organic waste generation.
All of the above factors are divided into attribute and target factors. Attribute factors are factors that describe the characteristics of households, such as size, type (e.g., single person, family), number, age, education, income of household members, geographical location of the household, etc. Target factors are factors that describe household organic waste, such as the total amount of waste generated and the types of organic waste.
Attribute and target factors can be classified according to different criteria, and some are more objective than others. For example, the size and number of household members are more objective than the type or education of household members.
Some factors are easier to control and have a greater impact on organic waste production than others. For example, the total amount of organic waste generated can be easily monitored using special containers, while the type and composition of organic waste is more difficult to track.
Based on these criteria, we have classified the attribute and target factors as follows:
(1)
Highly objective factors that are easy to monitor and have a significant impact on organic waste generation—size, number of members, type, income of the household.
(2)
Highly objective factors that are easy to monitor but have a lesser impact on organic waste generation—age, education of household members, geographical location of the household.
(3)
Low-objective factors, difficult to monitor, but with a potential impact on organic waste generation—type of diet, environmental awareness of the household.
The presented classification is used to select attribute and target factors in the association rule extraction algorithm. For example, high objective factors can be used to predict the total amount of organic waste, and low objective factors can be used to predict the types of organic waste.
The effect on the amount of organic waste generated by households is seasonal. In certain periods of the year, for example in the summer, when residents of households have vacations and vacations for pupils and students, the amount of organic waste generation increases accordingly. An equally important factor is the awareness of the population regarding waste. The presence of educational and informative educational activities on environmental topics can motivate residents to collect and process organic waste for the production of environmentally friendly energy. In addition to the mentioned factors, natural and climatic conditions have an influence on the amount of organic waste generated by households. They determine the possibility of growing fresh food, and their use affects the volume of organic waste generation.
On the basis of data analysis, conclusions and recommendations are made regarding their completeness and the possibility of use for the planning of circulating energy production for households. Also, on the basis of this stage, it is possible to achieve a reduction in the amount of unprocessed organic waste that is generated in a given territory. For example, by substantiating the feasibility of increasing the number of waste collection points or conducting an information campaign aimed at raising residents’ awareness of the feasibility of using waste for energy production and reducing the negative impact on the environment. After performing a preliminary analysis of data on the volumes of organic waste generation, households conduct their preparation. At the same time, they search for missed and anomalous data, and perform their cleaning and processing.
The next step in the algorithm for assessing the state of organic waste generation by community households is the selection of mathematical methods. One of the most common methods for identifying the factors that determine the efficiency of processes in various subject areas is to use the method of associative learning to find links between the volume of organic waste generation and the factors that cause it. The use of this method ensures the determination of the level of influence of factors on the generation of organic waste, which is the basis for the development of high-quality tools for managing the use of this waste.
The basis of our proposed algorithm is the method of associative analysis to identify the relationships between the factors that determine the volume of organic waste generated by community households. Associative Rule Learning is a machine learning method for data analysis that allows you to find patterns in large amounts of data and identify relationships between elements of a data set. The main task of associative learning is to find association rules between the elements of a data set. The substantiation of these rules will ensure the creation of accurate models for managing the use of household organic waste in specific communities.
The next step in the algorithm for assessing the state of organic waste generation by community households is the selection of mathematical methods. One of the most common methods for identifying the factors that determine the efficiency of processes in various subject areas is to use associative learning to find links between the volume of organic waste generation and the factors that cause it. The use of this method ensures the determination of the level of influence of factors on the generation of organic waste by households, which is the basis for the development of high-quality tools for managing the use of this waste.
If we denote the database with volumes of household organic waste generation and their factors by (H), and the number of households in this database N , then each household h i , i = 1 … N represents a certain set of households. We denote the support of the rule by S , and the probability by C .
The support S of an associative rule is the number of households that contain both the condition and the consequence. For example, A → B for an association, you can write:
S A → B = P A → B = n A ; B ∈ h i N ,
The probability C of an associative rule A → B is a measure of the accuracy of the rule and is defined as the ratio of the number of households containing the condition and the consequence to the number of households containing only the condition:
C A → B = P A → B = n 1 A ; B ∈ h i n 1 A ∈ h i ,
If the support and confidence are high enough, it is highly probable that any subsequent household that includes the condition will also include the consequence.
In addition to objective evaluations (support and confidence) of each of the generated rules, some subjective evaluations are used. All of them, in one way or another, are based on an objective. One of these indicators is interest lift L , determined by the formula:
L A → B = C A → B P B .
The larger the value of L , the more often the consequence is determined by the condition compared to the cases when the condition is absent. If L = 1 , there is no relationship, while values close to zero indicate a strong inverse relationship.
In some cases, the improvement indicator I is determined, which is the ratio of the frequency of observed rule execution to the product of the frequency of occurrence of the condition and the consequence separately:
I A → B = S A → B P B ⋅ P B .
At the same time, improvement I shows how many times the considered rule provides a correct forecast better than a random guess. All rules where I A → B ≤ 1 are not significant.
The methodology of the research involves the use of data mining, probability theory, mathematical statistics, machine learning technology and the Associative Rule Learning (ARL) method. Based on the use of a sound algorithm, they identify key trends and relationships between the factors of organic waste generation in communities in different countries, which is the basis for creating accurate models for forecasting the volume of collection and processing of this waste in communities.

4. The Results of Substantiation of Models of the State of Organic Waste Generation of Households in a Given Community

Our research was conducted for the conditions of the Lviv community (Lviv region, Ukraine). The municipal enterprise “Green City” is engaged in the collection and processing of household organic waste. To do this, they collect waste such as food scraps, leaves, branches and other plant and animal remains, which they use to produce compost. We analyzed 325 data sets according to 6 attributes: (1) “settlement_type”—type of settlement (village and township); (2) “household_type”—housing type (house and apartment); (3) “number_of_residents”—number of residents (persons); (4) “area”—the occupied area of the adjacent territory (m2); (5) “income_level”—income level of household residents (low, medium and high); and (6) “daily_waste_per_person”—daily volume of organic waste generation per inhabitant (kg/person) (Table 1).
Based on the processing of the received data, we have established the statistical characteristics of the numerical data by attributes: the number of residents (persons) (number_of_residents), the occupied area of the residential area (m2) (area) and the daily volume of organic waste generation per resident (kg/person) (daily_waste_per_person) (Table 2).
As for categorical data by attributes settlement type (settlement_type), housing type (household_type) and income level of household residents (income_level), based on their analysis, histograms of their number in the obtained sample were constructed (Figure 3).
It was established that organic waste from households was received from villages (58%) and from settlements (42%). The majority of organic waste from households came from individual houses (78%) and from apartments (22%). Such a percentage is typical for the built-up area around the city of Lviv. Regarding the incomes of residents of individual households, most of them have a low level of income (62%). The average and high level of income of households that received organic waste is 31% and 7%, respectively.
The obtained data indicate that in the territory of the Lviv community, the daily amount of organic waste generation per inhabitant ranges from 0.1 to 0.3 kg/person. The mean value is 0.192 kg/person, with a standard deviation of 0.058 kg/person. During the studied period, the largest number of households produced organic waste per inhabitant in the range of 0.14–0.25 kg/person. At the same time, most households have from 2 to 4 residents and are located on the territory of the house from 350 m2 to 680 m2.
Based on the analysis of interrelationships between the factors determining the daily volumes of organic waste generation by households per capita, it can be said that there are no close interrelationships between the factors. For a more detailed analysis, we built a correlation matrix with a heat map, which reflects the quantitative values of the correlation coefficients between the factors that determine the daily volume of organic waste generation by households per capita (Figure 4).
It was established that there are no close correlations between individual factors that determine the daily volume of organic waste generation by households per capita. In particular, the highest correlation coefficient is between the type of housing and the income level of household residents, which is 0.13. Regarding the daily volume of organic waste generated by households per capita, the number of residents and the occupied area of the home territory have the greatest influence. For a more in-depth analysis, dependencies between the specified factors were constructed (Figure 5).
Based on the comparison of the forms of the two probability distributions of the daily volumes of organic waste generation by households per capita, a graphical representation of how similar or different the positions, scale and asymmetry of the two distributions is given. The displayed slope and position of the linear regression between quantiles reflects the measure of relative location and the relative scale of individual households with their attributes in terms of household organic waste generation per capita. It has been established that for further research it is possible to use the theoretical model of the normal distribution of daily volumes of organic waste generation by households per capita (Figure 6).
The obtained results indicate that the lack of close interrelationships between the factors that determine the daily volume of organic waste generation by households per capita determines the use of machine learning algorithms for forecasting the volume of organic waste generation by households.
We constructed quantile–quantile (Q-Q) graphs for daily volumes of organic waste generation by households per capita (Figure 7).
It is suggested to use an a priori algorithm and association rules to assess the state of organic waste generation by households in a given community. The a priori algorithm is used to extract frequent sets of elements, which are further used to analyze association rules. In this algorithm, the user defines a minimum support, which is the minimum threshold that decides whether a set of elements is considered “frequent”.
Conducting such a study will provide recommendations for their use for circulating energy production. To perform the given task, we use an a priori algorithm and represent its association using the NetworkX library in Python for researching graphs and networks.
Based on the definition of the interest lift L indicator, we determine the probability of a given amount of organic waste generation by households Y, when factors X are given, while simultaneously controlling how frequent the amount of organic waste generation by households Y is. The obtained results are presented in Table 3.
Table 3 contains the characteristics of the association rules that were discovered using the a priori algorithm based on the input data.
Each row of the table represents one association rule, which consists of the preceding and following list of factors, as well as characteristics of this rule, such as:
(1)
Antecedents—the antecedent of the rule, i.e., the set of factors that are on the left side of the rule;
(2)
Consequents—consequent of the rule, i.e., a set of goods or factors that are on the right side of the rule;
(3)
Antecedent support—antecedent support, i.e., the frequency of antecedent occurrence in the data set;
(4)
Consequent support—support of the consequent, i.e., the frequency of occurrence of the consequent in the data set;
(5)
Support—rule support, i.e., the frequency of occurrence of antecedent and consequent together in the data set;
(6)
Confidence—the reliability of the rule, i.e., the probability that the consequent occurs if the antecedent occurs;
(7)
Lift—strengthening of the rule, i.e., the ratio of the observed reliability of the rule to the reliability that the rule could have by chance;
(8)
Leverage—the weight of the rule, i.e., the difference between the actually observed support of the rule and the support that the rule could have by chance;
(9)
Conviction—conviction of the rule, i.e., the ratio of the probability that the consequent does not occur when the antecedent occurs to the probability that the consequent does not occur if the antecedent does not occur.
On the basis of the conducted research, we constructed a diagram of the relationships between the factors determining the daily volume of organic waste generation by households per capita (Figure 8).
Table 3, with the association rules, and the diagram of relationships between factors (Figure 8) allows us to draw the following conclusions about relationships between factors influencing the volume of organic waste generation in households:
(1)
With small amounts of waste (little waste), there is a fairly high probability (support 0.53) that they come from a private house, which confirms the connection between reduced amounts of waste and a decrease in the probability of their generation in an apartment building;
(2)
With a low level of income (low) of the residents, there is almost the same probability that the residents live in a private house or an apartment building, and accordingly, a decrease in income does not affect the type of house from which organic waste comes;
(3)
At an average level of income (medium), the probability that organic waste comes from a private house is much higher (support 0.31), which may indicate that with an increase in the level of income, more people can afford to build private houses instead of living in apartment buildings;
(4)
The arrival of organic waste from the township reduces the probability of having a private house (confidence 0.76), which may be due to the fact that in towns near large cities (in our case, the city of Lviv), there is usually less space for the construction of private houses and more apartment buildings;
(5)
Receipt of organic waste from the village increases the probability of its generation in a private house (confidence 0.82), which may be due to the fact that there are more opportunities for the construction of private houses in villages, as well as a larger number of residents living in individual private houses in rural areas who can afford their own housing.
The results of our study show that the type of housing (private house or apartment building), the level of income of residents, and the location of the community (town or village) are all factors that influence the volume of organic waste generation in households. Our findings are consistent with the results of previous studies. For example, a study by [15] found that households in private houses generate more organic waste than households in apartment buildings. This is likely due to the fact that private houses often have larger yards and gardens, which can be used to grow food and compost organic waste.
Another study [6] found that households with higher incomes generate more organic waste than households with lower incomes. This is likely due to the fact that households with higher incomes can afford to purchase more food, which can lead to more food waste. Finally, a study by [10] found that households in rural areas generate more organic waste than households in urban areas. This is likely due to the fact that rural households often have larger yards and gardens, and are more likely to have livestock, which can generate manure.
Our study also found that the association between the type of housing and the volume of organic waste generation is influenced by the level of income of residents. For example, at an average level of income, the probability that organic waste comes from a private house is much higher than the probability that it comes from an apartment building. This suggests that with an increase in the level of income, more people can afford to build private houses, which can lead to an increase in the volume of organic waste generation. Our study also found that the arrival of organic waste from the township reduces the probability of having a private house. This may be due to the fact that in towns near large cities, there is usually less space for the construction of private houses and more apartment buildings.
Finally, our study found that receipt of organic waste from the village increases the probability of its generation in a private house. This is likely due to the fact that there are more opportunities for the construction of private houses in villages, as well as a larger number of residents living in individual private houses in rural areas who can afford their own housing. Overall, our study provides further evidence that the type of housing, the level of income of residents, and the location of the community are all factors that influence the volume of organic waste generation in households. This information can be used to develop targeted interventions to reduce organic waste generation in different types of communities.

5. Discussion of Research Results

Based on the analysis of the state of organic waste generation by households in the EU countries, it can be said that the use of household organic waste for the production of ecologically clean energy is an important component of sustainable energy development and environmental protection of individual countries. It was established that there is a weak relationship between the specific annual volume of organic waste and its share from household activities. This indicates that the volumes of organic waste generation, as well as their share from household activities, are influenced by a number of specific factors. They are characteristic of a particular settlement. At the same time, the quantitative values of organic waste generation per capita in different countries and their regions and communities may vary depending on various factors. To assess the state of organic waste generation by households of a given community, an approach should be proposed that takes into account their peculiarities and is based on modern information technologies. For this, an approach is proposed, the algorithm of which involves the implementation of eight stages. It is based on the method of associative analysis, which provides a qualitative search for connections between the volumes of organic waste generation and the factors that determine them for the conditions of a given community. In particular, the Associate Rule Learning (ARL) machine learning method used for data analysis makes it possible to find regularities in large volumes of data and to identify relationships between data set elements. The main task of associative learning is to find association rules between data set elements.
Based on the use of the proposed approach and the data of the utility company “Green City”, which collects and processes household organic waste, we substantiated models for assessing the state of generation of household organic waste in the settlements of the Lviv community (Lviv region, Ukraine). The obtained dependencies and models are the basis of qualitative forecasting and planning of collection and processing of organic waste from the households of the community. Based on the conducted research, it was established that there is a positive relationship between the type of settlement and the amount of organic waste generated in households. For example, residents of villages generate more organic waste than residents of villages. There is also a positive relationship between the type of house and the amount of organic waste generated in households. Residents who live in houses generate more waste than those who live in apartments. There is a positive relationship between household income and the amount of organic waste they generate. Households with higher incomes generate more organic waste than households with lower incomes.
The most important rules of association indicate that households with low resident incomes and correspondingly low levels of organic waste per capita are significantly less likely to generate large amounts of waste than households with higher resident incomes and higher levels of waste per capita.
Further research requires the collection of large data on the volumes of organic waste generation by households and their factors in different regions of the EU countries, which will provide the substantiation of models for forecasting the volumes of organic waste generation, which are the basis for qualitative coordination of the configuration of waste collection and processing systems to obtain ecologically clean energy for households.
One limitation of our study is that it is based on data from a single community in Ukraine. Therefore, our findings may not be generalizable to other communities. Another limitation of our study is that we did not collect data on other factors that may influence organic waste generation, such as the size of the household, the age of the residents, and the type of food that is consumed.
Future research should focus on collecting data from a larger sample of communities in Ukraine and other countries to assess the generalizability of our findings. Future research should also collect data on other factors that may influence organic waste generation, such as the size of the household, the age of the residents, and the type of food that is consumed.

6. Conclusions

The proposed approach to assessing the state of organic waste generation of households in a given community is presented in the form of an algorithm that involves the implementation of eight stages. It is based on the collection of real data on the generation of organic waste in a given territory, the intellectual analysis of this data using modern methods, as well as the use of the method of associative analysis to find connections between the volume of organic waste generation and the factors that determine it for the conditions of a given community. The systematic execution of the specified stages ensures the finding of regularities in large volumes of data, associative learning and the search for rules of association between elements of the data set, which is the basis of the justification of the model for assessing the state of organic waste generation of households in a given community.
Based on the proposed approach, Python 3.9 software was developed, which makes it possible to quickly perform calculations and perform a quantitative assessment of the state of organic waste generation by households of a given community according to the specified rules of association between the volumes of organic waste generation and their factors. Based on the use of the proposed approach and the data of the utility company “Green City”, which collects and processes household organic waste, we substantiated models for assessing the state of generation of household organic waste in the settlements of the Lviv community (Lviv region, Ukraine). The obtained dependencies and models are the basis of qualitative forecasting and planning of collection and processing of organic waste from the households of the community.

7. Research Gaps and Research Directions

Based on the results of the presented research, the following research gaps and research directions were determined:
  • It is necessary to test the approach on a larger sample of communities in Ukraine and other countries in order to assess its possibilities and carry out generalization. The proposed approach does not take into account factors that can affect the generation of organic waste, such as the size of the household, the age of the residents and the type of food consumed. It is necessary to collect data on these factors and evaluate their impact on the formation of organic waste.
  • The directions of further research are:
    (a)
    Data collection and consideration of other factors affecting the generation of organic waste in households;
    (b)
    Development of machine learning models for forecasting the generation and planning of organic waste processing, which take into account the well-founded interrelationships between the specified factors.
Research in these areas will help to develop more effective tools and improve organic waste management in communities.

Author Contributions

Conceptualization I.T. and T.H.; Methodology, A.C. and A.T.; Software A.T. and K.M.; Resources, S.G. and W.T.; Project administration, A.C.; Validation, I.T. and N.K.; Visualization S.G.; Data curation, A.B. and M.S.; Supervision T.H. All authors have read and agreed to the published version of the manuscript.

Funding

Financed from the subsidy of the Ministry of Education and Science for the Warsaw University of Life Sciences (SGGW) for the year 2023.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Data available in a publicly accessible repository.

Acknowledgments

The anonymous reviewers are gratefully acknowledged for their constructive review that significantly improved this manuscript, The National Centre for Research and Development as Programme Operator of the Programme “Applied Research” implemented under the European Economic Area Financial Mechanism (EEA FM) 2014–2021, and the Norwegian Financial Mechanism (NMF) 2014–2021, Scheme: Support for Ukrainian Researchers under Bilateral Fund.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Kaczmarczyk, B.; Lis, K. Perception of the Transition to a Zero-Emission Economy in the Opinion of Polish and Foreign Students: A Comparative Analysis. Energies 2023, 16, 6486. [Google Scholar] [CrossRef]
  2. Tryhuba, A.; Hutsol, T.; Tryhuba, I.; Mudryk, K.; Kukharets, V.; Głowacki, S.; Dibrova, L.; Kozak, O.; Pavlenko-Didur, K. Assessment of the Condition of the Project Environment for the Implementation of Technologically Integrated Projects of the “European Green Deal” Using Maize Waste. Energies 2022, 15, 8220. [Google Scholar] [CrossRef]
  3. Vaverková, M.D.; Adamcová, D. Municipal solid waste management and waste-to-energy in the United States: A review. Renew. Sustain. Energy Rev. 2018, 82, 3170–3177. [Google Scholar] [CrossRef]
  4. Zaikova, A.; Deviatkin, I.; Havukainen, J.; Horttanainen, M.; Fruergaard Astrup, T.; Saunila, M.; Happonen, A. Factors Influencing Household Waste Separation Behavior: Cases of Russia and Finland. Recycling 2022, 7, 52. [Google Scholar] [CrossRef]
  5. Wang, C.; Jiang, H.; Wu, H.; Guo, S.; Xu, M. Scaling in urban building energy use and its influencing factors. J. Ind. Ecol. 2023, 27, 1076–1088. [Google Scholar] [CrossRef]
  6. Cárdenas-González, M.; Lope-Valdivia, M.; Aguilera-Vázquez, M.; Cabañas-Moreno, J.G. Renewable energy from organic waste: A review of sustainable technologies. Renew. Energy 2018, 129, 457–467. [Google Scholar]
  7. Tryhuba, A.; Hutsol, T.; Tryhuba, I.; Pokotylska, N.; Kovalenko, N.; Tabor, S.; Kwasniewski, D. Risk Assessment of Investments in Projects of Production of Raw Materials for Bioethanol. Processes 2021, 9, 12. [Google Scholar] [CrossRef]
  8. Eurostat. Waste Statistics—Database. European Commission. 2023. Available online: https://ec.europa.eu/eurostat/web/waste/data/database (accessed on 23 July 2023).
  9. State Statistics Service of Ukraine. Main. Official Website. Available online: https://www.ukrstat.gov.ua/ (accessed on 28 July 2023).
  10. Nizami, A.S.; Rehan, M.; Waqas, M.; Naqvi, M.; Ouda, O.K. Organic Waste for Bioenergy and Bioproducts: Global Potential and Implications for Sustainable Resource Management. Renew. Sustain. Energy Rev. 2015, 45, 561–571. [Google Scholar] [CrossRef]
  11. Ozawa, S.; Takai, K.; Yamaguchi, T. Utilization of household waste as a renewable energy source in Japan. Waste Manag. 2012, 32, 1730–1735. [Google Scholar] [CrossRef]
  12. Koval, N.; Kondysiuk, I.; Grabovets, V.; Onyshchuk, V. Forecasting the fund of time for performance of works in hybrid projects using machine training technologies. In CEUR Workshop Proceedings; ITPM: Tokyo, Japan, 2021; Volume 2917, pp. 196–206. [Google Scholar]
  13. Ratushny, R.; Horodetskyy, I.; Molchak, Y.; Grabovets, V. The configurations coordination of the projects products of development of the community fire extinguishing systems with the project environment (ITPM-2021). In CEUR Workshop Proceedings; ITPM: Tokyo, Japan, 2021; Volume 2851. [Google Scholar]
  14. Bravi, M.; Girotto, F. Biowaste-to-biogas as an integral part of the circular economy concept: An Italian case study. Waste Manag. Res. 2022, 35, 1128–1133. [Google Scholar]
  15. Madden, B.; Florin, N.; Mohr, S.; Giurco, D. Emissions associated with the management of household organic waste, from collection to recovery and disposal: A bottom-up approach for Sydney and surrounding areas, Australia. Clean. Waste Syst. 2023, 6, 100111. [Google Scholar] [CrossRef]
  16. Yadvika, S.; Sreekrishnan, T.R.; Kohli, S.; Rana, V. Biogas production from different waste sources: A review. Renew. Sustain. Energy Rev. 2004, 8, 27–45. [Google Scholar]
  17. Boldrin, A.; Baratieri, M.; Malagoli, M.; Tiehm, A. Economic viability of biogas production from organic waste: A review. Renew. Sustain. Energy Rev. 2015, 51, 746–762. [Google Scholar]
  18. Boyarchuk, V.; Ftoma, O.; Francik, S.; Rudynets, M. Method and Software of Planning of the Substantial Risks in the Projects of Production of raw Material for Biofuel. In CEUR Workshop Proceedings; ITPM: Tokyo, Japan, 2020. [Google Scholar]
  19. Batyuk, B.; Dyndyn, M. Coordination of Configurations of Complex Organizational and Technical Systems for Development of Agricultural Sector Branches. J. Autom. Inf. Sci. 2020, 52, 63–76. [Google Scholar]
  20. Gerardi, M.H. (Ed.) The Microbiology of Anaerobic Digesters; John Wiley & Sons: Hoboken, NJ, USA, 2006; Volume 25. [Google Scholar]
  21. Bashynsky, O.; Garasymchuk, I.; Gorbovy, O.; Vilchinska, D.; Dubik, V. Research of the variable natural potential of the wind and energy energy in the northern strip of the ukrainian carpathians. In Proceedings of the 6th International Conference: Renewable Energy Sources (ICoRES 2019). E3S Web of Conferences, Krynica, Poland, 12–14 June 2019; EDP Sciences: Les Ulis, France, 2000; Volume 154, p. 06002. [Google Scholar]
  22. Levis, J.W.; Barlaz, M.A. Anaerobic biodegradability of six biopolymers. J. Environ. Sci. Health Part A 2011, 46, 1261–1270. [Google Scholar]
  23. Boyarchuk, V.; Ftoma, O.; Padyuka, R.; Rudynets, M. Forecasting the risk of the resource demand for dairy farms basing on machine learning (MoMLeT&DS-2020) In CEUR Workshop Proceedings; ITPM: Tokyo, Japan, 2000; Volume 2631. [Google Scholar]
  24. Paemanee, C.; Tontisirin, K. Life cycle assessment of electricity generation from organic waste: A case study in Thailand. Renew. Energy 2016, 93, 228–236. [Google Scholar]
  25. Ratushny, R.; Bashynsky, O.; Shcherbachenko, O. Identification of firefighting system configuration of rural settlements. In Proceedings of the Fire and Enviromnental Safety Engineering. MATEC Web Conferences, FESE, Lviv, Ukraine, 7–8 November 2018; Volume 247. [Google Scholar]
  26. Niemiec, M.; Sikora, J.; Szelag-Sikora, A.; Kubon, M.; Olech, E.; Marczuk, A. Applicability of food industry organic waste for methane fermentation. Przem. Chem. 2017, 96, 685–688. [Google Scholar] [CrossRef]
  27. Borek, K.; Romaniuk, W.; Roman, K.; Roman, M.; Kubon, M. The Analysis of a Prototype Installation for Biogas Production from Chosen Agricultural Substrates. Energies 2021, 14, 2132. [Google Scholar] [CrossRef]
  28. Sikora, J.; Niemiec, M.; Szeląg-Sikora, A.; Gródek-Szostak, Z.; Kuboń, M.; Komorowska, M. The Effect of the Addition of a Fat Emulsifier on the Amount and Quality of the Obtained Biogas. Energies 2020, 13, 1825. [Google Scholar] [CrossRef]
  29. Lisowska, A.; Filipek-Mazur, B.; Komorowska, M.; Niemiec, M.; Bar-Michalczyk, D.; Kuboń, M.; Tabor, S.; Gródek-Szostak, Z.; Szeląg-Sikora, A.; Sikora, J.; et al. Environmental and production aspects of using fertilizers based on waste elemental sulfur and organic materials. Materials 2022, 15, 3387. [Google Scholar] [CrossRef]
  30. Borg, K.; Boulet, M.; Karunasena, G.; Pearson, D. Segmenting households based on food waste behaviours and waste audit outcomes: Introducing over providers, under planners and considerate planners. J. Clean. Prod. 2022, 351, 131589. [Google Scholar] [CrossRef]
  31. Kumar, A.; Samadder, S.R. Municipal solid waste management in India: From waste disposal to recovery of resources? J. Mater. Cycles Waste Manag. 2018, 20, 1163–1166. [Google Scholar]
  32. Mata-Alvarez, J.; Macé, S.; Llabrés, P. Anaerobic digestion of organic solid wastes. An overview of research achievements and perspectives. Bioresour. Technol. 2000, 74, 3–16. [Google Scholar] [CrossRef]
  33. Bashynsky, O. Conceptual model of management of technologically integrated industry development projects. In Proceedings of the 15th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), Zbarazh, Ukraine, 23–26 September 2020; Volume 2, pp. 155–158. [Google Scholar]
  34. Montanarella, L.; Panagos, P. The relevance of sustainable soil management within the European Green Deal. Land Use Policy 2021, 100, 104950. [Google Scholar] [CrossRef]
  35. Tryhuba, A.; Boyarchuk, V.; Tryhuba, I.; Boyarchuk, O.; Ftoma, O. Evaluation of Risk Value of Investors of Projects for the Creation of Crop Protection of Family Daily Farms. Acta Univ. Agric. Silvic. Mendel. Brun. 2019, 67, 1357–1367. [Google Scholar] [CrossRef]
  36. Shahzad, K.; Ehsan, A.; Nawaz, A.; Irshad, M.; Rizwan, M.; Afzal, M. An integrated approach for energy recovery from organic waste: A review of global practices and future directions. Waste Manag. 2021, 120, 463–480. [Google Scholar] [CrossRef]
  37. Li, R.; Li, M.; Li, Y.; Li, W.; Li, X. Anaerobic digestion and gasification of food waste for energy recovery: A review. J. Clean. Prod. 2021, 318, 128523. [Google Scholar] [CrossRef]
  38. Zhai, Y.; Liu, L.; Yin, X.; Cao, J.; Bai, X. Comparative study on the performance of various organic waste-to-energy technologies. Renew. Sustain. Energy Rev. 2020, 127, 109874. [Google Scholar]
  39. Cai, Q.; Chen, T.; Yang, C. Characterization of kitchen waste in China and its potential for energy recovery. J. Clean. Prod. 2021, 299, 126882. [Google Scholar] [CrossRef]
  40. Koirala, K.; Gruening, C.; Brunner, P.H. Composting of food waste from households: An overview of challenges and potentials. J. Environ. Manag. 2020, 257, 110021. [Google Scholar] [CrossRef]
  41. Pardo, G.; Moral, R.; Bustamante, M.A. Biogas production from household food waste: The effects of particle size and bulking agents. Sci. Total Environ. 2021, 766, 142575. [Google Scholar] [CrossRef]
  42. Kiktev, N.; Osypenko, V.; Kalivoshko, O.; Kutyrev, A. Information system for decision-making in the management of renewable energy sources in the microgrid system. In CEUR Workshop Proceedings; ITPM: Tokyo, Japan, 2021; Volume 3018, pp. 101–110. [Google Scholar]
  43. Gharagozloo, S.; Ghazizade, M.J. The Influence of Socio-Economic and Psychological Factors on the Composition of Household Solid Waste in Farahzad Neighborhood. Environ. Health Insights 2023, 17, 11786302231195794. [Google Scholar] [CrossRef] [PubMed]
  44. Bongoni, R.; Sciubba, E.; Bonoli, A. Food waste management in European households: A critical review of practices and policy. J. Clean. Prod. 2020, 279, 123703. [Google Scholar] [CrossRef]
  45. Debono, D.; Sant, T. An assessment of the management of organic household waste in Malta. Waste Manag. 2021, 119, 310–318. [Google Scholar] [CrossRef]
  46. Rudynets, M.; Pavlikha, N.; Kytsyuk, I.; Komeliuk, O.; Fedorchuk-Moroz, V.; Androshchuk, I.; Skorokhod, I.; Seleznov, D. Establishing patterns of change in the indicators of using milk processing shops at a community territory. East.-Eur. J. Enterp. Technol. Control. Process. 2019, 3, 57–65. [Google Scholar]
  47. Ratushnyi, R.; Bashynsky, O.; Ptashnyk, V. Development and Usage of a Computer Model of Evaluating the Scenarios of Projects for the Creation of Fire Fighting Systems of Rural Communities. In Proceedings of the Xl-th International Scientific and Practical Conference on Electronics and Information Technologies (ELIT), Lviv, Ukraine, 16–18 September 2019; pp. 34–39. [Google Scholar]
  48. Palko, D.; Vialkova, V.; Babenko, T. Intellectual Models for Cyber Security Risk Assessment. Processing, Transmission and Security of Information; Wydawnictwo Naukowe Akademii Techniczno-Humanistycznej w Bielsku-Białej: Bielsku-Biała, Poland, 2019; Volume 2, pp. 284–288. [Google Scholar]
  49. Lub, P.; Padyuka, R.; Berezovetsky, S.; Chubyk, R. Simulation modeling usage in the information system for the technological systems project management. In CEUR Workshop Proceedings; ITPM: Tokyo, Japan, 2023; Volume 3453, pp. 139–148. [Google Scholar]
  50. Ratushny, R.; Bashynsky, O.; Ptashnyk, V. Planning of Territorial Location of Fire-Rescue Formations in Administrative Territory Development Projects. In CEUR Workshop Proceedings; ITPM: Tokyo, Japan, 2020. [Google Scholar]
  51. Vázquez-Rowe, I.; Villanueva-Rey, P.; Moreira, M.T. Household food waste prevention and management in Europe: A systematic review. J. Clean. Prod. 2021, 314, 128052. [Google Scholar] [CrossRef]
  52. Kukharets, V.; Juočiūnienė, D.; Sukmaniuk, O.; Čėsna, J.; Kukharets, S.; Piersa, P.; Szufa, S.; Horetska, I.; Shevtsova, A. An Algorithm for Managerial Actions on the Rational Use of Renewable Sources of Energy: Determination of the Energy Potential of Biomass in Lithuania. Energies 2023, 16, 548. [Google Scholar] [CrossRef]
  53. Rathore, P.; Sarmah, S.P. Investigation of factors influencing source separation intention towards municipal solid waste among urban residents of India. Resour. Conserv. Recycl. 2021, 164, 105164. [Google Scholar] [CrossRef]
  54. Kucher, O.; Hutsol, T.; Glowacki, S.; Andreitseva, I.; Dibrova, A.; Muzychenko, A.; Szeląg-Sikora, A.; Szparaga, A.; Kocira, S. Energy Potential of Biogas Production in Ukraine. Energies 2022, 15, 1710. [Google Scholar] [CrossRef]
  55. Tryhuba, A.; Komarnitskyi, S.; Tryhuba, I.; Yermakov, S.; Muzychenko, A.; Muzychenko, T.; Horetska, I. Planning and risk analysis in projects of procurement of agricultural raw materials for the production of environmentally friendly fuel. Int. J. Renew. Energy Dev. 2022, 11, 569–580. [Google Scholar] [CrossRef]
  56. Boryga, M.; Kołodziej, P. Reverse Engineering in Modeling Agricultural Products. Agric. Eng. 2022, 26, 105–117. [Google Scholar] [CrossRef]
  57. Prístavka, M.; Findura, P.; Beloev, I.; Kuboń, M.; Hrdá, V.; Kovalyshyn, S.; Shchur, T. Verification of the Measurement System in a Production Organization. Agric. Eng. 2022, 26, 81–90. [Google Scholar] [CrossRef]
Sustainability 15 15922 g002
Figure 2. The structure of influencing factors on the amount of organic waste generated by households in a given territory of the community.
Figure 2. The structure of influencing factors on the amount of organic waste generated by households in a given territory of the community.
Sustainability 15 15922 g002
Sustainability 15 15922 g003
Figure 3. Histograms of the number of categorical data values in the sample by attributes: settlement type (settlement_type), housing type (household_type) and income level of household residents (income_level).
Figure 3. Histograms of the number of categorical data values in the sample by attributes: settlement type (settlement_type), housing type (household_type) and income level of household residents (income_level).
Sustainability 15 15922 g003
Sustainability 15 15922 g004
Figure 4. Histogram of the largest number of households by daily generation of organic waste per capita.
Figure 4. Histogram of the largest number of households by daily generation of organic waste per capita.
Sustainability 15 15922 g004
Sustainability 15 15922 g005
Figure 5. Correlation matrix of factors determining the daily volume of organic waste generation by households per capita.
Figure 5. Correlation matrix of factors determining the daily volume of organic waste generation by households per capita.
Sustainability 15 15922 g005
Sustainability 15 15922 g006
Figure 6. Interrelationships between the factors determining the daily volume of organic waste generation by households per capita.
Figure 6. Interrelationships between the factors determining the daily volume of organic waste generation by households per capita.
Sustainability 15 15922 g006
Sustainability 15 15922 g007
Figure 7. Quantile–quantile (Q-Q) graphs for normal and logistic distributions of daily volumes of organic waste generation by households per capita.
Figure 7. Quantile–quantile (Q-Q) graphs for normal and logistic distributions of daily volumes of organic waste generation by households per capita.
Sustainability 15 15922 g007
Sustainability 15 15922 g008
Figure 8. Diagram of relationships between factors determining the daily volume of organic waste generation by households per capita.
Figure 8. Diagram of relationships between factors determining the daily volume of organic waste generation by households per capita.
Sustainability 15 15922 g008
Table 1. Initial data for assessing the state of household organic waste generation.
Table 1. Initial data for assessing the state of household organic waste generation.
IdSettlement_TypeHousehold_TypeNumber_of_ResidentsAreaIncome_LevelDaily_Waste_per_Person
0townshiphouse2493low0.20
1villageapartment2901high0.15
2villagehouse5486medium0.12
…………………
322townshipapartment1508low0.15
323villagehouse6661low0.17
324townshipapartment2323low0.23
Table 2. Statistical characteristics of numerical data regarding the state of organic waste generation of households.
Table 2. Statistical characteristics of numerical data regarding the state of organic waste generation of households.
IndexNumber of ResidentsAreaDaily Waste per Person
count325325325
mean3.4275120.192
std1.8772700.058
min1150.1
25%23090.14
50%34990.19
75%46800.25
max1116230.3
Table 3. Characteristics of association rules.
Table 3. Characteristics of association rules.
Rule NoAntecedentsConsequentsAntecedent SupportConsequent SupportSupportConfidenceLiftLeverageConviction
0(little waste)(house)0.530.790.430.811.030.011.12
1(low)(house)0.600.790.470.791.000.000.99
2(medium)(house)0.310.790.260.841.070.021.33
3(township)(house)0.520.790.400.760.970.000.88
4(village)(house)0.480.790.390.821.040.011.17
5(low, little waste)(house)0.330.790.260.791.000.001.01
6(little waste, village)(house)0.270.790.230.841.070.011.33
7(low, township)(house)0.330.790.260.780.980.000.93
8(low, village)(house)0.270.790.220.801.020.001.07
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Tryhuba, I.; Hutsol, T.; Tryhuba, A.; Cieszewska, A.; Kovalenko, N.; Mudryk, K.; Glowacki, S.; Bryś, A.; Tulej, W.; Sojak, M. An Approach to Assessing the State of Organic Waste Generation in Community Households Based on Associative Learning. Sustainability 2023, 15, 15922. https://doi.org/10.3390/su152215922

AMA Style

Tryhuba I, Hutsol T, Tryhuba A, Cieszewska A, Kovalenko N, Mudryk K, Glowacki S, Bryś A, Tulej W, Sojak M. An Approach to Assessing the State of Organic Waste Generation in Community Households Based on Associative Learning. Sustainability. 2023; 15(22):15922. https://doi.org/10.3390/su152215922

Chicago/Turabian Style

Tryhuba, Inna, Taras Hutsol, Anatoliy Tryhuba, Agata Cieszewska, Nataliia Kovalenko, Krzysztof Mudryk, Szymon Glowacki, Andrzej Bryś, Weronika Tulej, and Mariusz Sojak. 2023. "An Approach to Assessing the State of Organic Waste Generation in Community Households Based on Associative Learning" Sustainability 15, no. 22: 15922. https://doi.org/10.3390/su152215922

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop