Search results

Small-scale farmers are highly heterogeneous with regard to their types of farming, levels of technology adoption, degree of commercialization and many other factors. Such heterogeneous types, respectively groups of small-scale farming systems require different forms of government interventions. This paper applies a machine learning approach to analyze the typologies of small-scale farmers in South Africa based on a wide range of objective variables regarding their personal, farm and context characteristics, which support an effective, target-group-specific design and communication of policies.

A cluster analysis is performed based on a comprehensive quantitative and qualitative survey among 212 small-scale farmers, which was conducted in 2019 in the Limpopo Province of South Africa. An unsupervised machine learning approach, namely Partitioning Around Medoids (PAM), is applied to the survey data. Subsequently, the farmers' risk perceptions between the different clusters are analyzed and compared.

According to the results of the cluster analysis, the small-scale farmers of the investigated sample can be grouped into four types: subsistence-oriented farmers, semi-subsistence livestock-oriented farmers, semi-subsistence crop-oriented farmers and market-oriented farmers. The subsequently analyzed risk perceptions and attitudes differ considerably between these types.

This is the first typologisation of small-scale farmers based on a comprehensive collection of quantitative and qualitative variables, which can all be considered in the analysis through the application of an unsupervised machine learning approach, namely PAM. Such typologisation is a pre-requisite for the design of more target-group-specific and suitable policy interventions.

Subway systems are highly susceptible to external disturbances from emergencies, triggering a series of consequences such as the paralysis of the internal network transportation functions, causing significant economic and safety losses to cities. Therefore, it is necessary to analyze the factors affecting the resilience of the subway system to reduce the impact of disaster incidents.

Using the interval type-2 fuzzy linguistic term set and the K-medoids clustering algorithm, this paper improves the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method to construct a subway resilience factor analysis model for emergencies. Through comparative analysis, this study confirms the superior performance of the proposed approach in enhancing the precision of the DEMATEL method.

The results indicate that the operation and management level of emergency command organizations is the key resilience factors of subway operations in China. Furthermore, based on real case analyses, the corresponding suggestions and measures are put forward to improve the overall operation resilience level of the subway.

This paper identifies four emergency scenarios and 15 resilience factors affecting subway operations through literature review and expert consultation. The improved fuzzy DEMATEL method is applied to explore the levels of influence and causal mechanisms among the resilience factors of the subway system under the four emergency scenarios.

The Multi-Stakeholder Recommendation System learns consumer and producer preferences to make fair and balanced recommendations. Exclusive consumer-focused studies have improved the recommendation accuracy but lack in addressing producers' priorities for promoting their diverse items to target consumers, resulting in minimal utility gain for producers. These techniques also neglect latent and implicit stakeholders' preferences across item categories. Hence, this study proposes a personalized diversity-based optimized multi-stakeholder recommendation system by developing the deep learning-based diversity personalization model and establishing the trade-off relationship among stakeholders.

The proposed methodology develops the deep autoencoder-based diversity personalization model to investigate the producers' latent interest in diversity. Next, this work builds the personalized diversity-based objective function by evaluating the diversity distribution of producers' preferences in different item categories. Next, this work builds the multi-stakeholder, multi-objective evolutionary algorithm to establish the accuracy-diversity trade-off among stakeholders.

The experimental and evaluation results over the Movie Lens 100K and 1M datasets demonstrate that the proposed models achieve the minimum average improvement of 40.81 and 32.67% over producers' utility and maximum improvement of 7.74 and 9.75% over the consumers' utility and successfully deliver the trade-off recommendations.

The proposed algorithm for measuring and personalizing producers' diversity-based preferences improves producers' exposure and reach to various users. Additionally, the trade-off recommendation solution generated by the proposed model ensures a balanced enhancement in both consumer and producer utilities.