Development of the Enhanced Piece-Wise Linear Neural Network Algorithm

This chapter discusses development, application, and enhancement of a decomposition neural network rule extraction algorithm for nonlinear regression problems. The dual objectives of developing the algorithms are (1) to generate good predictive models comparable in performance to the original artificial neural network (ANN) models and (2) to “open up” the black box of a neural network model and provide explicit information in the form of rules that are expressed as linear equations. The enhanced PWL-ANN algorithm improves upon the PWL-ANN algorithm because it can locate more than two breakpoints and better approximate the hidden sigmoid activation functions of the ANN. Comparison of the results produced by the two versions of the PWL-ANN algorithm showed that the enhanced PWL-ANN models provide higher predictive accuracies and improved fidelities compared to the originally trained ANN models than the PWL-ANN models.

Comparing Deep Reinforcement Learning Algorithms’ Ability to Safely Navigate Challenging Waters

Reinforcement Learning (RL) controllers have proved to effectively tackle the dual objectives of path following and collision avoidance. However, finding which RL algorithm setup optimally trades off these two tasks is not necessarily easy. This work proposes a methodology to explore this that leverages analyzing the performance and task-specific behavioral characteristics for a range of RL algorithms applied to path-following and collision-avoidance for underactuated surface vehicles in environments of increasing complexity. Compared to the introduced RL algorithms, the results show that the Proximal Policy Optimization (PPO) algorithm exhibits superior robustness to changes in the environment complexity, the reward function, and when generalized to environments with a considerable domain gap from the training environment. Whereas the proposed reward function significantly improves the competing algorithms’ ability to solve the training environment, an unexpected consequence of the dimensionality reduction in the sensor suite, combined with the domain gap, is identified as the source of their impaired generalization performance.

TASC-MADM: Task Assignment in Spatial Crowdsourcing Based on Multiattribute Decision-Making

The methodology, formulating a reasonable task assignment to find the most suitable workers for a task and achieving the desired objectives, is the most fundamental challenge in spatial crowdsourcing. Many task assignment approaches have been proposed to improve the quality of crowdsourcing results and the number of task assignment and to limit the budget and the travel cost. However, these approaches have two shortcomings: (1) these approaches are commonly based on the attributes influencing the result of task assignment. However, different tasks may have different preferences for individual attributes; (2) the performance and efficiency of these approaches are expected to be improved further. To address the above issues, we proposed a task assignment approach in spatial crowdsourcing based on multiattribute decision-making (TASC-MADM), with the dual objectives of improving the performance as well as the efficiency. Specifically, the proposed approach jointly considers the attributes on the quality of the worker and the distance between the worker and the task, as well as the influence differences caused by the task’s attribute preference. Furthermore, it can be extended flexibly to scenarios with more attributes. We tested the proposed approach in a real-world dataset and a synthetic dataset. The proposed TASC-MADM approach was compared with the RB-TPSC and the Budget-TASC algorithm using the real dataset and the synthetic dataset; the TASC-MADM approach yields better performance than the other two algorithms in the task assignment rate and the CPU cost.

Deconstructing the Role of Adult Facilitators in Research Led by Young People

Academia and practice have increased their investment in young peoples’ participation. One key approach has been the shift from extracting data from young people to engaging them as researchers. Drawing on 2 case studies with young Syrian refugees and Bangladeshi young people, this paper critically reflects on the tensions between participation, power, and ethics whilst engaging young people as lead researchers. There are dual objectives to young people-led research: (a) the empowerment of young people as investigators and (b) the study of issues important to young people. If not clearly established from the outset, these objectives may be in conflict. In such projects, the process and methodology work to achieve the aims of the study and young people’s participation. The achievement of both objectives of young people-led research is partially dependent on adult facilitators’ support of the research process. This article explores the role of adult professionals towards achieving the goals of rigorous research and young people’s participation. These tensions commonly surface in research with young people and should be addressed by employing sensitive approaches that recognise young people as competent social actors with the ability to engage in research whilst taking into consideration relevant adult engagement and support.

How Productive Are the Microfinance Institutionsin Bangladesh? An Application of Malmquist Productivity Index

The poverty reduction and financial inclusion of Sustainable Development Goals (SDG) by 2030 can be significantly facilitated by the microfinance industry. However, it is pertinent to assess the sustainability of microfinance institutions (MFIs) in serving this purpose. The estimation of productivity of MFIs in Bangladesh gives a glimpse of their ability to fulfil the dual objectives of financial sustainability and social outreach. Hence, this study aims to measure the productivity of MFIs in Bangladesh using secondary data obtained from the Microfinance Information Exchange (MIX) market. The study employs Malmquist Productivity Index (MPI), which is an extension of the Data Envelopment Analysis (DEA) to estimate the overall, social and financial productivities of 26 MFIs in Bangladesh during the period from 2009 to 2018. In general, this study revealed that majority of the MFIs’ overall productivity score varies between 0.9 and 1.20. Moreover, we observed that the social and financial productivities of MFIs in Bangladesh progressed during the entire study period, except for the years 2011 and 2017. This development may be attributed to the average growth in catch-up and technological effect witnessed during the study period. The study has also applied sensitivity analysis by changing the output to evaluate the robustness of the overall productivity results; consequently, the new estimates followed a similar pattern (mostly) and further corroborate the outcomes of this study. JEL Codes: C14, O43, G21

Impact of Efficiency on Voluntary Disclosure of Non-Banking Financial Company—Microfinance Institutions in India

This paper investigates how the financial and social efficiency of firms influence the extent of the voluntary disclosure of Non-Banking Financial Companies–Micro Financial Institutions (NBFC-MFI). The study constructed an unweighted index of voluntary disclosure to estimate the level of voluntary disclosure of all of the included firms from the years 2015–2019. The financial and social efficiency, which is analogous to the technical efficiency of production theory and analyses both sustainability and outreach, respectively, was estimated using data envelopment analysis (DEA). The panel data analysis was completed, and a positive association of financial efficiency was estimated. The social efficiency was found to have no relationship to the voluntary disclosure level. This paper contributed to the literature by providing new determinants of voluntary disclosure. The study examines the econometric model and suggests that financially sustainable firms that utilize these resources well are more open to outsiders, while socially efficient firms are reluctant to voluntary disclosure, which also includes social activities, and consider this as a wasteful activity. The findings of this study are relevant to industry practitioners and regulators, who need to think upon the sustainability of this crucial sector by meeting the dual objectives of financial and social performance. This study is helpful to all stakeholders as well as for the government, who can use the results to design additional rules for the NBFC–MFI. This study will also help firms to design disclosure strategies to ascertain goodwill and less cost of capital, with easy access to funds.

Community narratives and local impacts of invasion in the Eastern Cape: A critical invasion ethnography of black wattle

Since 1995, the South African government has spearheaded a national invasive species campaign known as the Working for Water Program with the dual objectives of invasive species eradication and rural development. This national narrative on invasive species reflects a politicized research agenda and a wealth of material resources directed toward eradication, yet does not accurately portray the reality of invasion at the village level. In particular, Acacia mearnsii de Wild, or the black wattle tree, is classified as one of the worst invasive species in South Africa and a primary target for Working for Water, yet represents an important livelihood resource for rural communities and impacts community members differentially. To better understand these local rural realties, I use a critical invasion science approach to interrogate the local experiences and narratives of black wattle invasion in a rural pastoral community in the Eastern Cape. Within this community, local understandings and impacts of black wattle are nuanced, spatially variable, and reflect complex knowledge politics and political economies. As invasion research moves to incorporate the human and local dimension of invasion for improved policy, it is imperative to fully consider this differentiation of perspectives and impacts within the local community.

Annual dynamics of Zymoseptoria tritici populations in wheat cultivar mixtures: a compromise between the efficiency and durability of a recently broken-down resistance gene?

Cultivar mixtures slow polycyclic epidemics but may also modify the evolution of pathogen populations by diversifying the selection pressures exerted by their plant hosts at field scale. We compared the dynamics of natural populations of the fungal pathogen Zymoseptoria tritici in pure stands and in three binary mixtures of wheat cultivars (one susceptible cultivar and one cultivar carrying the recently broken-down Stb16q gene) over two annual field epidemics. We combined analyses of population ‘size’ based on disease severity, and of population ‘composition’ based on assessments of changes in the frequency of virulence against Stb16q in seedling assays with more than 3000 strains. In the field, disease levels were lower in mixtures, with each cultivar providing the other with reciprocal protection. The three cultivar proportions in the mixtures (0.25, 0.5 and 0.75) modulated the decrease in (i) the size of the pathogen population relative to the two pure stands, (ii) the size of the virulent subpopulation, and (iii) the frequency of virulence relative to the pure stand of the cultivar carrying Stb16q. Our findings suggest that optimal proportions may differ slightly between the three indicators considered. We identified potential trade-offs that should be taken into account when deploying a resistance gene in cultivar mixtures: between the dual objectives ‘efficacy’ and ‘durability’, and between the ‘size’ and ‘frequency’ of the virulent subpopulation. Based on current knowledge, it remains unclear whether virulent subpopulation size or frequency has the largest influence on interepidemic virulence transmission.

Effects from containment and closure policies to market quality: Do they really matter in Vietnam during Covid-19?

During the Covid-19 pandemic, the Vietnamese government has actively implemented various policies to achieve dual objectives: (i) to minimize the loss of life due to the infection; and (ii) to support economic growth. This paper is conducted to examine the effect of the government’s containment and closure policy on the stock market quality in Vietnam. Unlike other papers, we focus exclusively on market quality during the pandemic. We find that the policies appear to positively affect the market quality, except for closing-school policy (negative effect) and international travel (no effect). We argue that the government should sustain the policies until the wide availability of the vaccine to support the stock market quality in the near future.