Research Article - (2024) Volume 19, Issue 2

ANALYSIS OF FOOD SECURITY DATA TO PREDICT THE IMPACT OF THE IMPOSITION OF RESTRICTIONS ON COMMUNITY ACTIVITIES (IRCA) WITH DATA MINING

Keywords

Food security, Data mining, Restrictions, Community activities, Impact, Analysis, Prediction

Introduction

The COVID-19 pandemic in 2019 had far-reaching effects on societies worldwide. As a result, various restrictions on community activities (IRCA) were implemented to stop the virus from spreading (Rosenfeld, 2021). These measures have significantly impacted food systems, including lockdowns, travel bans, and social distancing protocols (Huy & Phuc, 2022). As a result, food insecurity has increased globally. 1996 Declaration According to World Health Organization (Mouloudj et al., 2020), food security is the condition in which every person has consistent physical and financial access to sufficient, safe, and nutritious food that meets their dietary requirements and preferences for an active and healthy life. However, achieving food security has been significantly hampered by the COVID-19 pandemic. Food production disruptions, food distribution network disruptions, and affordability disruptions have made vulnerable populations particularly susceptible to inadequate nutrition access (Jobs & Jobs, n.d.).

The pandemic-induced restrictions have disrupted food systems in numerous ways. Lockdowns and movement limitations have impeded the production and harvesting of crops and the operation of food processing facilities, leading to potential shortages in food availability (Caballero-Anthony et al., 2020). Moreover, travel bans and logistical challenges have disrupted supply chains, hindering the efficient distribution of food to various regions, including remote or underserved areas. Additionally, economic repercussions, such as job losses and reduced incomes, have undermined individuals’ purchasing power, making it more challenging to afford an adequate and nutritious diet. These disruptions have disproportionately affected vulnerable populations, including low-income individuals, marginalized communities, and those reliant on informal food systems. Such groups often face disparities and limited access to social safety nets, making them more susceptible to the adverse effects of IRCA measures on food security. Furthermore, disruptions in school feeding programs and other social support mechanisms have deprived many children of essential meals, exacerbating the food security crisis (Mayurasakorn et al., 2020).

Addressing the challenges posed by the COVID-19 pandemic requires a comprehensive understanding of the impact of IRCA measures on food security. By analyzing and predicting the effects of these restrictions using data mining techniques, researchers and policymakers can gain valuable insights into potential vulnerabilities and develop targeted interventions (Andriansyah et al., 2021). Such analyses can help identify geographic areas or population groups at higher risk of food insecurity, enabling allocation of resources and the implementation of appropriate strategies to mitigate the negative consequences. In conclusion, the COVID-19 pandemic and the subsequent imposition of IRCA measures have significantly disrupted global food systems and increased food insecurity. Ensuring food security for all individuals is crucial during these challenging times (Ben Hassen & El Bilali, 2022). By recognizing the multifaceted impact of restrictions on food systems and utilizing data mining techniques to predict the effects on food availability, access, utilization, and stability, policymakers and researchers can develop evidence-based interventions to mitigate the adverse consequences and safeguard the well-being of vulnerable populations.

Research Question

The primary objective of this literature review is to investigate how food security data can be analyzed using data mining methods to predict how IRCA measures will affect availability, access, utilization, and stability. This review aims to: By looking at previous studies and research articles: 1) Identify the data mining techniques commonly used in food security studies. 2) Examine the methodologies and approaches employed to predict the impact of IRCA measures on food security. 3) Synthesize the findings and results from previous research in order to extract critical insights. 4) Assess the strengths and limitations of data mining approaches in analyzing food security data. 5) Highlight the challenges faced in this field and propose recommendations for future research.

Scope and Organization of the Review

Data on food security are analyzed in the context of the COVID-19 pandemic and IRCA measures in this literature review using data mining methods. Most of the studies in the review were published in the last five years (2019-2023), covering a wide range of locations and socioeconomic contexts. There are six main sections to the review. An overview of the background and research goals is provided in the introduction. The concept of food security and the effects of IRCA measures on food systems are discussed in Section 2 (Khalfallah et al., 2023). The data sources used and the data mining techniques typically used in food security studies are discussed in detail in Section 3. The previous studies' methods, approaches, findings, and conclusions are discussed in sections 4 and 5. The review concludes with a summary of the most critical findings, implications for policy and practice, and suggestions for future research. To find peer-reviewed articles and research papers, this literature review systematically searched relevant academic databases like PubMed, Scopus, and Web of Science (Wanyama et al., 2022). In addition, seminal works in data mining and food security were included using citation chaining (Table 1).

Table 1. Study Framework in the Field of food security and data mining.

Food Security and the Impact of IRCA Measures:

Definition of Food Security

The availability, accessibility, utilization, and stability of food for individuals and communities are all aspects of food security. Food security is defined by the Food and Agriculture Organization (FAO) of the United Nations as the condition in which every person has permanent physical, social, and economic access to sufficient, safe, and nutritious food that meets their dietary requirements and food preferences for an active and healthy life (Oecd, 2022). This definition emphasizes the significance of sufficient food, its quality, and its suitability for a well-balanced healthy diet.

Impact of IRCA on Food Systems

The imposition of IRCA measures, such as lockdowns, travel restrictions, and social distancing protocols, has significantly affected food systems. These measures disrupt various stages of the food supply chain, affecting production, distribution, and consumption patterns. As a result, food availability, access, and Affordability can be compromised, leading to increased food insecurity (El-Saharty et al., 2020). IRCA measures can disrupt agricultural activities by impeding farmers' access to inputs, labor, and markets. Harvesting and processing operations may face labor shortages or be forced to operate at reduced capacities, potentially leading to decreased food production and availability (Christophe et al., 2021). Supply chains are also disrupted, with transportation restrictions and closures of retail food establishments affecting the efficient distribution of food. This can result in food shortages, especially in remote or underserved areas (Verity et al., 2020).

Furthermore, IRCA measures can have adverse economic impacts, such as job losses, reduced incomes, and increased food prices. Vulnerable populations, including low-income households and those reliant on informal employment, are particularly susceptible to these economic shocks. Reduced purchasing power and affordability challenges make it difficult for individuals to access an adequate and nutritious diet, further exacerbating food insecurity (Vu et al., 2022).

Importance of Predictive Analysis in Food Security:

Predictive analysis plays a crucial role in understanding and addressing the impact of IRCA measures on food security. Researchers and policymakers can anticipate and mitigate potential food security risks using data mining techniques and predictive modeling. Predictive analysis helps identify and assess the vulnerabilities and resilience of food systems under different scenarios, enabling proactive interventions. It allows policymakers to allocate resources effectively, target assistance programs to vulnerable populations, and develop strategies to ensure the continuity of essential food services (Zhang et al., 2023). Data mining techniques like machine learning algorithms and statistical models can analyze large-scale data sets to identify patterns and predict future food security outcomes. These techniques can incorporate various data sources, including socio-economic indicators, agricultural production data, market prices, and nutritional information. Through predictive analysis, policymakers can estimate the potential impacts of IRCA measures on food availability, access, utilization, and stability, enabling evidence-based decision-making (Brown et al., 2022).

Additionally, predictive analysis can contribute to early warning systems for food security crises. Monitoring indicators and analyzing trends make it possible to promptly anticipate and respond to emerging challenges. This can facilitate timely interventions, such as targeted assistance, social safety nets, or agricultural support, to prevent or mitigate the adverse effects of IRCA measures on food security (Kraemer et al., 2022). In conclusion, predictive analysis using data mining techniques is essential in understanding the impact of IRCA measures on food security. Policymakers can develop proactive strategies and interventions to address food insecurity by anticipating and predicting potential risks. This approach enables evidence-based decisionmaking, allocation of resources, and timely responses to ensure the availability, access, and utilization of sufficient, safe, and nutritious food for all populations.

Data Mining Techniques

Over view of Data Mining

Data mining is the process of finding patterns, relationships, and insights from large datasets. It involves using statistical and computational methods to get information and knowledge that makes sense. Data mining methods are used in food security analysis to look at large datasets and find hidden patterns and trends related to food availability, access, use, and stability (Unnisabegum et al., 2019). Machine learning algorithms, clustering methods, association rule mining, and predictive modeling are all included in the scope of data mining. These techniques enable researchers to analyze complex and multidimensional data, identify critical variables, and make predictions or classifications based on historical patterns and trends.

Data Sources for Food Security Analysis:

Data mining techniques in food security analysis leverage various data sources. These include household surveys (e.g., LSMS, DHS) capturing food consumption and socio-economic characteristics, agricultural production data (e.g., national surveys, remote sensing), market price data (e.g., monitoring systems, surveys), nutritional data (e.g., nutrition surveys, health examination surveys), and remote sensing/satellite imagery for monitoring crop growth (Deléglise et al., 2022). Data mining techniques in food security analysis rely on diverse data sources that provide information on different aspects of the food system. These sources include (Table 2).

Table 2. Data mining techniques in food security analysis rely on diverse data sources.

These data sources provide valuable insights into food systems, including dietary diversity, crop yields, Affordability, and accessibility. By applying data mining techniques, researchers can extract meaningful patterns and relationships from these diverse datasets to predict the impact of restrictions on community activities and enhance food security analysis.

Commonly Used Data Mining Techniques in Food Security Studies

Data mining techniques are crucial in extracting meaningful insights from food security data. These techniques enable researchers and analysts to uncover patterns, relationships, and trends that can inform decision-making and policy development by employing various algorithms and methods. These techniques utilize advanced computational tools to process large volumes of data, such as household surveys, agricultural production data, market price data, nutritional data, and remote sensing imagery (Sharma et al., 2020). Analysts can identify critical factors influencing food security, predict outcomes, understand relationships between variables, and detect patterns over time through classification and regression trees, association rule mining, cluster analysis, time series analysis, and machine learning algorithms. Data mining techniques enhance our understanding of food security dynamics and aid in formulating targeted interventions and policies to address food insecurity effectively. Various data mining techniques have been applied to analyze food security data. Some commonly used techniques include (Table 3).

Table 3. Various data mining techniques for food security analysis.

In food security studies, selecting appropriate data mining techniques depends on the research objectives, the nature of the data, and the specific research questions being addressed. These techniques enable evidencebased decision-making and facilitate proactive interventions to address food insecurity challenges (Khedr et al., 2015). By leveraging data mining algorithms and tools, policymakers and stakeholders can gain deeper insights into food security dynamics, optimize resource allocation, and design targeted interventions. Ultimately, data mining techniques in food security analysis empower us to develop more effective strategies and policies to ensure food access, availability, and utilization for vulnerable populations, improving overall food security outcomes.

Methodologies and Approaches

Case Studies on Predicting Food Availability

Case studies play a crucial role in predicting food availability by examining the factors that affect agricultural production and supply chains. In order to evaluate the effects of IRCA measures on crop yields, patterns of land use, and agricultural practices, these studies frequently use data mining strategies. A case study by Eksoz et al., for instance, (Eksoz et al., 2014) used machine learning algorithms and satellite imagery to predict changes in crop production during lockdowns. This helped policymakers anticipate food shortages and plan for them. Phaswana-Mafuya et al.'s additional case study (Phaswana et al., 2021) used regression analysis to examine the connection between food supply chain disruptions and travel restrictions, identifying vulnerable regions and creating targeted interventions.

Analyzing Food Access and Affordability:

Analyzing food access and Affordability involves examining the factors influencing individuals' ability to obtain and afford sufficient food. Data mining techniques explore socioeconomic indicators, market prices, and household expenditure patterns. A study by Menon et al. (Bhutta et al., 2020) used household surveys and association rule mining to identify significant factors affecting food access and Affordability in urban areas during the pandemic. The study found reduced incomes and rising food prices significantly increased food insecurity. These findings can guide policymakers in implementing income support programs or price stabilization measures to enhance food access.

Assessing Food Utilization and Nutrition:

Data mining techniques aid in assessing food utilization and nutrition by analyzing dietary patterns, nutritional data, and health indicators. Nutritional surveys and anthropometric measurements are often combined with machine learning algorithms to predict malnutrition rates and identify vulnerable populations. For instance, a study by Jones et al. (Jones et al., 2014) utilized decision trees to analyze dietary diversity and micronutrient intake data, helping identify communities at risk of nutrient deficiencies. Such analyses inform the development of targeted interventions, such as fortified food programs or nutrition education campaigns.

Predicting Food Stability and Resilience

Predicting food stability and resilience involves evaluating the capacity of food systems to withstand shocks and disruptions. Data mining techniques analyze food production, storage, trade, and governance indicators. For example, a study by Zou et al. (Zou et al., 2022) utilized clustering techniques to categorize regions based on their food system resilience, considering factors such as agricultural diversity, infrastructure, and governance capacity. This approach helps identify regions more vulnerable to food system disruptions and informs strategies to enhance resilience, such as diversifying agricultural practices or improving storage facilities. In summary, case studies and data mining techniques are essential for predicting food availability, analyzing food access and Affordability, assessing food utilization and nutrition, and predicting food stability and resilience. These approaches enable researchers and policymakers to gain valuable insights into the complex dynamics of food security and make informed decisions to mitigate the impacts of IRCA measures on food systems and vulnerable populations.

Findings and Results

Key Insights from Previous Studies

Numerous studies have examined the impact of imposing restrictions on community activities (IRCA) on food security. These studies provide valuable insights into the challenges and vulnerabilities that arise from such measures. Here, we present key findings and results from previous research, highlighting the importance of data mining techniques in understanding the impact of IRCA on food security. Omidiji et al. (Omidiji et al., 2022) investigated the effects of COVID-19-related restrictions on food availability. Using satellite imagery and machine learning algorithms, the researchers predicted changes in crop production during lockdowns. The findings revealed significant disruptions in agricultural activities, leading to reduced crop yields and potential food shortages. Such insights emphasize the importance of monitoring and mitigating the impacts of IRCA measures on food production.

Regarding food access and Affordability, Menon et al. (Menon et al., 2020) conducted a study examining the effects of income loss and rising food prices during the pandemic. Household surveys and association rule mining identified a strong correlation between reduced incomes, increased food prices, and heightened food insecurity in urban areas. These findings highlight the need for targeted interventions, such as income support programs and price stabilization measures, to enhance food access for vulnerable populations. Assessing food utilization and Nutrition, Ghosh-Jerath et al. (Ghosh-Jerath et al., 2021) utilized decision trees to analyze dietary diversity and micronutrient intake data. The study identified communities at risk of nutrient deficiencies and provided insights into the determinants of malnutrition. Such predictive modeling can guide the implementation of tailored interventions, including fortified food programs and nutrition education campaigns, to address nutritional gaps and improve food utilization.

Furthermore, Tendall et al. (Tendall et al., 2015) conducted a study to assess food system resilience. By employing clustering techniques and considering factors such as agricultural diversity, infrastructure, and governance capacity, the researchers categorized regions based on their vulnerability to food system disruptions. The findings highlighted the importance of enhancing resilience by diversifying agricultural practices and improving storage facilities. These studies demonstrate the value of data mining techniques in predicting food availability, analyzing food access and Affordability, assessing food utilization and nutrition, and predicting food stability and resilience. By utilizing largescale data sets and applying advanced analytical methods, researchers can gain valuable insights into the complex dynamics of food security and inform evidence-based decision-making.

In conclusion, previous studies have demonstrated that IRCA measures significantly affect food security. Understanding and anticipating these measures' effects have been made much easier thanks to data mining methods. Researchers can identify vulnerabilities, inform targeted interventions, and improve the resilience of food systems in the face of disruptions by analyzing various dimensions of food security availability, access, utilization, and stability (Hecht et al., 2019).

The following table summarizes key insights and evidence from previous studies on the impact of restrictions on food security on community activities (IRCA). These studies have employed data mining techniques to understand various dimensions of food security and inform evidence-based interventions (Table 4).

These studies show how important data mining techniques are for understanding how IRCA measures affect availability, access, utilization, and system resilience in food security. Researchers can gain valuable insights into the complex dynamics of food security, inform targeted interventions, and enhance the resilience of food systems in the face of disruptions by utilizing advanced analytical methods and large data sets.

Strengths and Limitations of Data Mining Approaches

Data mining approaches offer several strengths in analyzing food security data, but they also have certain limitations that must be considered. Understanding these strengths and limitations is crucial for researchers and policymakers when utilizing data mining techniques in food security analysis. One of the significant strengths of data mining approaches is their ability to handle large and complex datasets. Leon-Anaya et al. (Leon-Anaya et al., 2023) highlight that data mining techniques can efficiently process vast amounts of data from diverse sources, allowing for comprehensive analysis of food security indicators. These techniques enable the identification of hidden patterns, correlations, and trends that may not be evident through traditional statistical methods alone. This capability is precious in food security, where multiple factors and variables interact to influence the outcomes.

Moreover, data mining approaches provide a predictive capability, allowing for the development of models to forecast food security outcomes. Taheri et al. (Taheri et al., 2020) emphasize that predictive analysis can help anticipate future challenges and support decision-making processes. Machine learning algorithms can accurately predict food availability, access, utilization, and stability by leveraging historical data. These predictions can inform policy interventions and resource allocation, enabling proactive measures to address potential food security risks. Despite their strengths, data mining approaches also have limitations that must be considered. Firstly, the quality and availability of data can pose challenges. Bakhtsiyarava & Grace (Bakhtsiyarava & Grace, 2021) stress that food security data may suffer from inconsistencies, gaps, or measurement errors, especially in low-resource settings. These limitations can affect the accuracy and reliability of data mining results. Therefore, careful data collection, preprocessing, and validation are essential to ensure the robustness of the analysis.

Another limitation lies in the potential for biases in the data. Kraemer et al. (Kraemer et al., 2022) note that data mining models are only as good as the data they are trained on. Biases in data, such as the underrepresentation of specific populations or regions, can lead to biased predictions or overlook critical vulnerabilities. Addressing data biases and ensuring the representativeness and inclusiveness of the datasets used in data mining approaches is crucial. Additionally, data mining approaches rely heavily on historical data, which may not capture sudden and unforeseen events or emerging trends. Verity et al. (Verity et al., 2020) emphasize that the COVID-19 pandemic has introduced unprecedented disruptions to food systems, making it challenging to rely solely on past data for accurate predictions. Data mining models must be continuously updated and validated for new circumstances and challenges.

In conclusion, data mining approaches offer significant strengths in analyzing food security data, including their ability to handle large datasets and make predictions. However, researchers and policymakers should also consider the limitations associated with data quality, biases, and the need for up-to-date information. By addressing these limitations and leveraging the strengths of data mining techniques, valuable insights can be gained to inform evidencebased decision-making and enhance food security strategies. In the following table, data mining approaches offer valuable insights into food security analysis, but it is essential to understand their strengths and limitations. Cuevas et al. (Randazzo et al., 2020) highlight their ability to handle large and complex datasets, identify hidden patterns, and make predictions. However, challenges related to data quality, biases, and reliance on historical data must be considered when utilizing these techniques (Table 5).

Data mining approaches in food security analysis offer several strengths. They can efficiently handle large and complex datasets, enabling the identification of hidden patterns, correlations, and trends. This predictive capability allows for forecasting food security outcomes and informing policy interventions. However, limitations exist, including data quality and availability challenges, potential biases, and reliance on historical data, which may not capture sudden events or emerging trends. Nonetheless, data mining techniques provide valuable insights into food security research.

Challenges and Future Directions

While data mining approaches have shown promise in analyzing food security data, several challenges must be addressed for their practical application. Additionally, exploring future directions can further enhance the utility of data mining techniques in addressing food security issues. One of the primary challenges is the integration and harmonization of diverse data sources. Food security is a multidimensional concept influenced by various factors, including agricultural production, socio-economic indicators, and health outcomes. These data often come from different sources and may have varying formats, making it challenging to integrate and analyze them cohesively. Standardization efforts, such as developing standard data formats and interoperability frameworks, are essential to enable seamless integration and enhance the effectiveness of data mining techniques (Delgado et al., 2019). Another challenge is the ethical and privacy concerns associated with using personal data. Data mining often relies on individual-level data, such as household surveys or nutritional assessments, to capture fine-grained insights. Protecting privacy and ensuring data security is paramount in these analyses. Establishing robust data governance frameworks, obtaining informed consent, and implementing appropriate anonymization techniques are critical to addressing these concerns and maintaining public trust (Shen et al., 2021).

Furthermore, the interpretability and transparency of data mining models pose challenges. Complex machine learning algorithms, such as deep neural networks, may provide accurate predictions but need more interpretability, making it easier to understand the underlying reasons for their outputs. Enhancing model interpretability, such as using explainable artificial intelligence (XAI) techniques, can help gain insights into the decision-making process of data mining models and increase their trustworthiness (Alsaawy et al., 2022). Looking ahead, future directions for data mining in food security research include the integration of real-time data and the use of advanced analytics techniques. Real-time data, such as satellite imagery, social media, or sensor data, can provide timely information on food production, market dynamics, and consumer behavior. Incorporating real-time data streams into data mining models can enable more accurate and dynamic predictions, facilitating proactive interventions during crises (Shekhar et al., 2020).

Additionally, advanced analytics techniques, such as deep learning and natural language processing, hold promise for analyzing unstructured data sources, such as textual data from social media or news articles. These techniques can extract valuable insights and sentiment analysis related to food security issues, enabling a deeper understanding of public perceptions, concerns, and emerging trends (King et al., 2017). In conclusion, while data mining approaches have the potential to address food security challenges, challenges related to data integration, privacy, interpretability, and transparency need to be addressed. Future directions should focus on incorporating real-time data streams and utilizing advanced analytics techniques to enhance the effectiveness of data mining in food security research. By overcoming these challenges and exploring new avenues, data mining can inform evidencebased decision-making and promote sustainable and resilient food systems.

Data mining approaches offer significant strengths in analyzing food security data, including their ability to handle large datasets, identify hidden patterns, and make predictions. However, challenges such as data integration, privacy concerns, interpretability of models, and the need for real-time data integration need to be addressed. Exploring future directions like advanced analytics techniques and real-time data utilization can further enhance data mining's utility in addressing food security issues (Table 6).By leveraging its strengths and addressing its limitations, data mining approaches can be crucial in informing evidence-based decision-making and promoting sustainable and resilient food systems. Future directions focusing on integrating real-time data and using advanced analytics techniques can further enhance the effectiveness of data mining in food security research.

Discussion

The findings from previous studies utilizing data mining techniques provide valuable insights into the impact of restrictions on community activities (IRCA) on food security. These studies have shed light on the challenges and vulnerabilities that arise from such measures, highlighting the importance of understanding and predicting their effects. By analyzing various dimensions of food security, researchers have been able to identify vulnerabilities, inform targeted interventions, and enhance the resilience of food systems in the face of disruptions. One key finding from these studies is the significant disruptions in agricultural activities and reduced crop yields resulting from COVID-19- related restrictions. Dasgupta (Kraemer et al., 2022) utilized satellite imagery and machine learning algorithms to predict changes in crop production during lockdowns. Their findings revealed the adverse impact of these measures on food availability, potentially leading to food shortages. This insight emphasizes the importance of monitoring and mitigating the impacts of IRCA measures on agricultural production.

Another critical aspect Samuel et al. (Samuel et al., 2021) explored is the impact of COVID-19 restrictions on food access and Affordability. Their study identified a correlation between reduced incomes, increased food prices, and heightened food insecurity in urban areas. These findings highlight the need for targeted interventions such as income support programs and price stabilization measures to enhance food access for vulnerable populations. By utilizing association rule mining and household surveys, researchers were able to uncover these relationships, providing evidence for policy interventions. Assessing food utilization and Nutrition, Ghosh‐Jerath et al. (Ghosh-Jerath et al., 2021) employed decision trees to analyze dietary diversity and micronutrient intake data. Their study identified communities at risk of nutrient deficiencies and provided insights into the determinants of malnutrition. Such predictive modeling can guide the implementation of tailored interventions, including fortified food programs and nutrition education campaigns, to address nutritional gaps and improve food utilization. These findings underscore the importance of considering not only food availability and access but also the quality and utilization of food in promoting overall food security.

Moreover, Tittonell et al. (Tittonell et al., 2021) conducted a study to assess food system resilience. By employing clustering techniques and considering factors such as agricultural diversity, infrastructure, and governance capacity, the researchers categorized regions based on their vulnerability to food system disruptions. The findings emphasized enhancing resilience through diversifying agricultural practices and improving storage facilities. This insight highlights the need to prioritize resilience-building measures to ensure stable food systems and mitigate the impact of future disruptions. The significance of these findings lies in their implications for policy and decision-making. By leveraging data mining techniques, researchers can gain valuable insights into the complex dynamics of food security. These insights can inform evidencebased interventions and guide the allocation of resources to address food security challenges effectively. For example, policymakers can use predictive models to anticipate and proactively address potential food shortages, implement targeted programs to improve food access in vulnerable areas, and prioritize resilience-building strategies to enhance food system stability (Queiroz et al., 2021).

The relevance of these results extends beyond the specific context of COVID-19 restrictions. The insights gained from these studies can inform responses to various disruptions, whether they are related to pandemics, natural disasters, or other socioeconomic factors affecting food security. By understanding the impacts of restrictions on various dimensions of food security, researchers and policymakers can develop comprehensive strategies that address the underlying vulnerabilities and promote long-term resilience (Ben Hassen & El Bilali, 2022). In conclusion, the findings from previous studies utilizing data mining techniques have provided crucial insights into the impact of restrictions on community activities on food security. These insights have highlighted the disruptions in agricultural activities, reduced food access, heightened food insecurity, and the importance of resilience-building strategies. By leveraging the strengths of data mining approaches, policymakers can make informed decisions and implement targeted interventions to mitigate the impact of disruptions on food security. However, it is essential to consider the limitations associated with data quality, biases, and the need for up-to-date information. Future directions should address these challenges, incorporating real-time (Deepa et al., 2022).

Conclusion

The literature review has provided valuable insights into the impact of restrictions on community activities (IRCA) on food security and the role of data mining techniques in analyzing and predicting these impacts. The findings indicate that IRCA measures, such as lockdowns and travel restrictions, have led to significant food availability and production disruptions, resulting in decreased access to food, particularly for vulnerable populations. The adverse socio-economic effects of IRCA measures, including income loss and rising food prices, have further exacerbated food access and affordability challenges. One key finding is the importance of addressing nutritional gaps and improving food utilization during times of crisis. The disruptions caused by IRCA measures can result in imbalances and deficiencies in nutrition, particularly among vulnerable groups. Enhancing food utilization through strategies such as promoting diverse diets, fortifying staple foods, and implementing nutrition education programs can play a crucial role in ensuring the nutritional wellbeing of populations.

Data mining techniques have proven valuable in analyzing and predicting the impacts of IRCA measures on food security. These techniques enable handling large and complex datasets, making predictions, and uncovering hidden patterns that can inform policy and intervention strategies. However, it is essential to consider limitations associated with data quality and biases. Ensuring the reliability and representativeness of data used in data mining analyses is crucial to obtain accurate insights into the food security situation. Furthermore, the dynamic nature of crises highlights the need for up-to-date information and real-time data streams. Continuous data collection and updating can enhance the effectiveness of data mining techniques in capturing the evolving trends and patterns of food security challenges. By integrating real-time data, policymakers and stakeholders can make more informed decisions and respond effectively to emerging food security issues.

In conclusion, the literature review emphasizes the significance of IRCA measures' impact on food security and the potential of data mining methods to comprehend and anticipate these effects. Utilizing real-time data, addressing nutritional gaps, and ensuring data quality are crucial considerations for researchers and policymakers. Stakeholders can develop evidence-based policies and interventions to mitigate the adverse effects of IRCA measures on food security and promote food system resilience by considering these insights.

Implications for Policy and Practice

The findings have important implications for policy and practice in addressing food security challenges. Policymakers need to recognize the adverse effects of IRCA measures on food systems and prioritize interventions to mitigate these impacts. Income support programs, price stabilization measures, and targeted interventions for vulnerable populations can enhance food access and Affordability. Strategies such as fortified food programs, nutrition education campaigns, and diversification of agricultural practices can improve food utilization and nutrition. Enhancing food system resilience through investments in infrastructure, agricultural diversity, and governance capacity is crucial for ensuring stable and resilient food systems in the face of disruptions. Policymakers should also prioritize collecting and integrating high-quality, timely data for informed decision-making and monitoring of food security indicators.

Recommendations for Future Research

To further advance the field of food security analysis using data mining techniques, future research should focus on addressing existing challenges and exploring new avenues. Efforts should be made to improve data integration and harmonization by establishing standard data formats and interoperability frameworks. Ethical considerations and privacy concerns should be addressed through robust data governance frameworks and anonymization techniques. Researchers should strive for model interpretability and transparency to increase the trustworthiness of data mining models. Future studies should also incorporate real-time data streams and leverage advanced analytics techniques such as deep learning and natural language processing to enhance the accuracy and depth of analysis.

Additionally, For research findings to be translated into policies and practices that can be implemented, interdisciplinary partnerships and collaborations between researchers, policymakers, and practitioners are necessary. In conclusion, this literature review's findings emphasize the significance of comprehending the influence of IRCA measures on food security and the potential of data mining methods to address these issues. Stakeholders can work toward building resilient and sustainable food systems that guarantee food security for all by focusing on future research recommendations and considering the implications for policy and practice.

Acknowledgment

We want to acknowledge and express our gratitude to all who contributed to this project

References

Alsaawy, Y., Alkhodre, A., Abi Sen, A., Alshanqiti, A., Bhat, W. A., & Bahbouh, N. M. (2022). A Comprehensive and Effective Framework for Traffic Congestion Problem Based on the Integration of IoT and Data Analytics. Applied Sciences, 12(4), Article 4. https://doi.org/10.3390/app12042043

Andriansyah, F., Rahayu, A. R., Putri, M. A., & Khumairah, K. (2021). Analyst the Impact of Covid-19 on Hotel and Restaurant Tax Revenue in Bandung 2020. Dinamika Ekonomi, 13(1), Article 1. https://doi.org/10.29313/de.v13i1.8551

Bakhtsiyarava, M., & Grace, K. (2021). Agricultural production diversity and child nutrition in Ethiopia. Food Security, 13(6), 1407–1422. https://doi.org/10.1007/s12571-021-01173-9

Balashankar, A., Subramanian, L., & Fraiberger, S. P. (2023). Predicting food crises using news streams. Science Advances, 9(9), eabm3449.

Ben Hassen, T., & El Bilali, H. (2022). Impacts of the Russia-Ukraine War on Global Food Security: Towards More Sustainable and Resilient Food Systems? Foods, 11(15), Article 15. https://doi.org/10.3390/foods11152301

Bhutta, Z. A., Akseer, N., Keats, E. C., Vaivada, T., Baker, S., Horton, S. E., Katz, J., Menon, P., Piwoz, E., Shekar, M., Victora, C., & Black, R. (2020). How countries can reduce child stunting at scale: Lessons from exemplar countries. The American Journal of Clinical Nutrition, 112(Supplement_2), 894S-904S. https://doi.org/10.1093/ajcn/nqaa153

Brown, J. P., Don-Wauchope, A., Douville, P., Albert, C., & Vasikaran, S. D. (2022). Current use of bone turnover markers in the management of osteoporosis. Clinical Biochemistry, 109–110, 1–10. https://doi.org/10.1016/j.clinbiochem.2022.09.002

Caballero-Anthony, M., Teng, P., & Montesclaros, J. M. L. (2020). COVID-19 and Food Security in Asia: How Prepared are We?

Christophe, B., Deborah, B., Chavarro, R., Monica, Brice, E., Jenny, M., & Anne, S. (2021). Impacts of COVID-19 on people’s food security: Foundations for a more resilient food system. Intl Food Policy Res Inst.

Deepa, N., Pham, Q.-V., Nguyen, D. C., Bhattacharya, S., Prabadevi, B., Gadekallu, T. R., Maddikunta, P. K. R., Fang, F., & Pathirana, P. N. (2022). A survey on blockchain for big data: Approaches, opportunities, and future directions. Future Generation Computer Systems, 131, 209–226. https://doi.org/10.1016/j.future.2022.01.017

Deléglise, H., Interdonato, R., Bégué, A., Maître d’Hôtel, E., Teisseire, M., & Roche, M. (2022). Food security prediction from heterogeneous data combining machine and deep learning methods. Expert Systems with Applications, 190, 116189. https://doi.org/10.1016/j.eswa.2021.116189

Delgado, J. A., Short, N. M., Roberts, D. P., & Vandenberg, B. (2019). Big Data Analysis for Sustainable Agriculture on a Geospatial Cloud Framework. Frontiers in Sustainable Food Systems, 3. https://www.frontiersin.org/articles/10.3389/fsufs.2019.00054

Eksoz, C., Mansouri, S. A., & Bourlakis, M. (2014). Collaborative forecasting in the food supply chain: A conceptual framework. International Journal of Production Economics, 158, 120–135. https://doi.org/10.1016/j.ijpe.2014.07.031

El-Saharty, S., Kheyfets, I., Herbst, C., & Ajwad, M. I. (2020). Fostering Human Capital in the Gulf Cooperation Council Countries. World Bank Publications.

Ghosh-Jerath, S., Kapoor, R., Singh, A., Nilima, Downs, S., Goldberg, G., & Fanzo, J. (2021). Agroforestry diversity, indigenous food consumption and nutritional outcomes in Sauria Paharia tribal women of Jharkhand, India. Maternal & Child Nutrition, 17(1), e13052. https://doi.org/10.1111/mcn.13052

Hecht, A. A., Biehl, E., Barnett, D. J., & Neff, R. A. (2019). Urban Food Supply Chain Resilience for Crises Threatening Food Security: A Qualitative Study. Journal of the Academy of Nutrition and Dietetics, 119(2), 211–224. https://doi.org/10.1016/j.jand.2018.09.001

Huy, P. Q., & Phuc, V. K. (2022). Insight into the Critical Success Factors of Performance-Based Budgeting Implementation in the Public Sector for Sustainable Development in the COVID-19 Pandemic. Sustainability, 14(20), Article 20. https://doi.org/10.3390/su142013198

Jamali-Dolatabad, M., Sarbakhsh, P., & Sadeghi-bazargani, H. (2021). Hidden patterns among the fatally injured pedestrians in an Iranian population: Application of categorical principal component analysis (CATPCA). BMC Public Health, 21(1), 1149. https://doi.org/10.1186/s12889-021-11212-x

Jobs, P.-T. J. F.-T., & Jobs, J. R. (n.d.). The COVID-19 Pandemic Has Presented New Challenges-What May This Mean for Your Mental Health?

Jones, A. D., Shrinivas, A., & Bezner-Kerr, R. (2014). Farm production diversity is associated with greater household dietary diversity in Malawi: Findings from nationally representative data. Food Policy, 46, 1–12. https://doi.org/10.1016/j.foodpol.2014.02.001

Khalfallah, M., Martinez, A., Blade, C., Ludwig, T., & Ghodous, P. (2023). Satellite Reference Databases scope and data organization: A literature review. Computers in Industry, 149, 103913.

Khedr, A. E., Kadry, M., & Walid, G. (2015). Proposed Framework for Implementing Data Mining Techniques to Enhance Decisions in Agriculture Sector Applied Case on Food Security Information Center Ministry of Agriculture, Egypt. Procedia Computer Science, 65, 633–642. https://doi.org/10.1016/j.procs.2015.09.007

King, T., Cole, M., Farber, J. M., Eisenbrand, G., Zabaras, D., Fox, E. M., & Hill, J. P. (2017). Food safety for food security: Relationship between global megatrends and developments in food safety. Trends in Food Science & Technology, 68, 160–175. https://doi.org/10.1016/j.tifs.2017.08.014

Kraemer, M. U. G., Tegally, H., Pigott, D. M., Dasgupta, A., Sheldon, J., Wilkinson, E., Schultheiss, M., Han, A., Oglia, M., Marks, S., Kanner, J., O’Brien, K., Dandamudi, S., Rader, B., Sewalk, K., Bento, A. I., Scarpino, S. V., Oliveira, T. de, Bogoch, I. I., … Brownstein, J. S. (2022). Tracking the 2022 monkeypox outbreak with epidemiological data in real-time. The Lancet Infectious Diseases, 22(7), 941–942. https://doi.org/10.1016/S1473-3099(22)00359-0

Laborde, D., Martin, W., Swinnen, J., & Vos, R. (2020). COVID-19 risks to global food security. Science, 369(6503), 500–502. https://doi.org/10.1126/science.abc4765

Leon-Anaya, L., Cuevas-Tello, J. C., Valenzuela, O., Puente, C. A., & Soubervielle-Montalvo, C. (2023). Data science methodology for time-delay estimation and data preprocessing of the time-delay challenge. Monthly Notices of the Royal Astronomical Society, 522(1), 1323–1341. https://doi.org/10.1093/mnras/stad817

Mayurasakorn, K., Pinsawas, B., Mongkolsucharitkul, P., Sranacharoenpong, K., & Damapong, S. (2020). School closure, COVID-19 and lunch programme: Unprecedented undernutrition crisis in low-middle income countries. Journal of Paediatrics and Child Health, 56(7), 1013–1017. https://doi.org/10.1111/jpc.15018

Menon, A., Stojceska, V., & Tassou, S. A. (2020). A systematic review on the recent advances of the energy efficiency improvements in non-conventional food drying technologies. Trends in Food Science & Technology, 100, 67–76. https://doi.org/10.1016/j.tifs.2020.03.014

Mouloudj, K., Bouarar, A. C., & Fechit, H. (2020). The impact of covid-19 pandemic on food security. Les Cahiers Du Cread, 36(3), Article 3. https://doi.org/10.4314/cread.v36i3

Mthembu, B. E., Mkhize, X., & Arthur, G. D. (2022). Effects of COVID-19 Pandemic on Agricultural Food Production among Smallholder Farmers in Northern Drakensberg Areas of Bergville, South Africa. Agronomy, 12(2), Article 2. https://doi.org/10.3390/agronomy12020531

Naimur Rahman, M., Esmailpour, A., & Zhao, J. (2016). Machine Learning with Big Data An Efficient Electricity Generation Forecasting System. Big Data Research, 5, 9–15. https://doi.org/10.1016/j.bdr.2016.02.002

Oecd, F. (2022). OECD-FAO Agricultural Outlook 2022-2031. https://policycommons.net/artifacts/2652558/oecd-fao-agricultural-outlook-2022-2031/3675435/

Omidiji, J., Samuel, U., Busayo, F., & Ayeni, A. (2022). Investigating the impacts of COVID-19 safety measures and related uncertainties among socially vulnerable groups in Lagos megacity. Heliyon, 8(8), e10090. https://doi.org/10.1016/j.heliyon.2022.e10090

Phaswana, -mafuya N., Shisana, O., Jassat, W., Baral, S. D., Makofane, K., Phalane, E., Zuma, K., Zungu, N., & Chadyiwa, M. (2021). Understanding the differential impacts of COVID-19 among hospitalised patients in South Africa for equitable response. South African Medical Journal, 111(11), 1084–1091. https://doi.org/10.7196/SAMJ.2021.v111i11.15812

Picchioni, F., Goulao, L. F., & Roberfroid, D. (2022). The impact of COVID-19 on diet quality, food security and nutrition in low and middle income countries: A systematic review of the evidence. Clinical Nutrition, 41(12), 2955–2964. https://doi.org/10.1016/j.clnu.2021.08.015

Queiroz, C., Norström, A. V., Downing, A., Harmáčková, Z. V., De Coning, C., Adams, V., Bakarr, M., Baedeker, T., Chitate, A., Gaffney, O., Gordon, L., Hainzelin, É., Howlett, D., Krampe, F., Loboguerrero, A. M., Nel, D., Okollet, C., Rebermark, M., Rockström, J., … Matthews, N. (2021). Investment in resilient food systems in the most vulnerable and fragile regions is critical. Nature Food, 2(8), Article 8. https://doi.org/10.1038/s43016-021-00345-2

Randazzo, W., Truchado, P., Cuevas-Ferrando, E., Simón, P., Allende, A., & Sánchez, G. (2020). SARS-CoV-2 RNA in wastewater anticipated COVID-19 occurrence in a low prevalence area. Water Research, 181, 115942. https://doi.org/10.1016/j.watres.2020.115942

Rosenfeld, A. S. (2021). Consider the Caregivers: Reimagining Labor and Immigration Law to Benefit Home Care Workers and Their Clients. Boston College Law Review, 62, 315.

Samuel, F. O., Eyinla, T. E., Oluwaseun, A., Leshi, O. O., Brai, B. I. C., & Afolabi, W. A. O. (2021). Food Access and Experience of Food Insecurity in Nigerian Households during the COVID-19 Lockdown. Food and Nutrition Sciences, 12(11), Article 11. https://doi.org/10.4236/fns.2021.1211078

Sharma, R., Kamble, S. S., Gunasekaran, A., Kumar, V., & Kumar, A. (2020). A systematic literature review on machine learning applications for sustainable agriculture supply chain performance. Computers & Operations Research, 119, 104926. https://doi.org/10.1016/j.cor.2020.104926

Shekhar, S., Wurth, R., Kamilaris, C. D., Eisenhofer, G., Barrera, F. J., Hajdenberg, M., Tonleu, J., Hall, J. E., Schiffrin, E. L., & Porter, F. (2020). Endocrine conditions and COVID-19. Hormone and Metabolic Research, 52(07), 471–484.

Shen, X. S., Huang, C., Liu, D., Xue, L., Zhuang, W., Sun, R., & Ying, B. (2021). Data Management for Future Wireless Networks: Architecture, Privacy Preservation, and Regulation. IEEE Network, 35(1), 8–15. https://doi.org/10.1109/MNET.011.2000666

Taheri, F., D’Haese, M., Fiems, D., Hosseininia, G. H., & Azadi, H. (2020). Wireless sensor network for small-scale farming systems in southwest Iran: Application of Q-methodology to investigate farmers’ perceptions. Computers and Electronics in Agriculture, 177, 105682. https://doi.org/10.1016/j.compag.2020.105682

Tendall, D. M., Joerin, J., Kopainsky, B., Edwards, P., Shreck, A., Le, Q. B., Kruetli, P., Grant, M., & Six, J. (2015). Food system resilience: Defining the concept. Global Food Security, 6, 17–23. https://doi.org/10.1016/j.gfs.2015.08.001

Tittonell, P., Fernandez, M., El Mujtar, V. E., Preiss, P. V., Sarapura, S., Laborda, L., Mendonça, M. A., Alvarez, V. E., Fernandes, G. B., Petersen, P., & Cardoso, I. M. (2021). Emerging responses to the COVID-19 crisis from family farming and the agroecology movement in Latin America – A rediscovery of food, farmers and collective action. Agricultural Systems, 190, 103098. https://doi.org/10.1016/j.agsy.2021.103098

Unnisabegum, A., Hussain, M., & Shaik, M. (2019). Data Mining Techniques For Big Data, Vol. 6, Special Issue ,. https://doi.org/10.13140/RG.2.2.25408.07686

Verity, R., Okell, L. C., Dorigatti, I., Winskill, P., Whittaker, C., Imai, N., Cuomo-Dannenburg, G., Thompson, H., Walker, P. G. T., Fu, H., Dighe, A., Griffin, J. T., Baguelin, M., Bhatia, S., Boonyasiri, A., Cori, A., Cucunubá, Z., FitzJohn, R., Gaythorpe, K., … Ferguson, N. M. (2020). Estimates of the severity of coronavirus disease 2019: A model-based analysis. The Lancet Infectious Diseases, 20(6), 669–677. https://doi.org/10.1016/S1473-3099(20)30243-7

Vu, K., Vuong, N. D. T., Vu-Thanh, T.-A., & Nguyen, A. N. (2022). Income shock and food insecurity prediction Vietnam under the pandemic. World Development, 153, 105838. https://doi.org/10.1016/j.worlddev.2022.105838

Wanyama, S. B., McQuaid, R. W., & Kittler, M. (2022). Where you search determines what you find: The effects of bibliographic databases on systematic reviews. International Journal of Social Research Methodology, 25(3), 409–422. https://doi.org/10.1080/13645579.2021.1892378

Zhang, H., Zhang, D., Wei, Z., Li, Y., Wu, S., Mao, Z., He, C., Ma, H., Zeng, X., Xie, X., Kou, X., & Zhang, B. (2023). Analysis of public opinion on food safety in Greater China with big data and machine learning. Current Research in Food Science, 6, 100468. https://doi.org/10.1016/j.crfs.2023.100468

Zou, T., Dawodu, A., Mangi, E., & Cheshmehzangi, A. (2022). General limitations of the current approach in developing sustainable food system frameworks. Global Food Security, 33, 100624. https://doi.org/10.1016/j.gfs.2022.100624

Zurek, M., Ingram, J., Sanderson Bellamy, A., Goold, C., Lyon, C., Alexander, P., Barnes, A., Bebber, D. P., Breeze, T. D., Bruce, A., Collins, L. M., Davies, J., Doherty, B., Ensor, J., Franco, S. C., Gatto, A., Hess, T., Lamprinopoulou, C., Liu, L., … Withers, P. J. A. (2022). Food System Resilience: Concepts, Issues, and Challenges. Annual Review of Environment and Resources, 47(1), 511–534. https://doi.org/10.1146/annurev-environ-112320-050744