University of Energy and Natural Resources

This research assesses the role of climate variability in aquaculture development and its growth among stakeholders in Ghana's Upper East Region, a dry zone marked by unpredictable precipitation and growing climate instability. Conducted within the Kasena Nankana Municipal Area, the study focused on the Tono irrigation project's catchment area, which spans approximately 1,674 square kilometres, with 80 percent of the area being terrestrial. The investigation utilized descriptive and statistical methods to analyse both secondary and primary datasets. Data collection involved questionnaires, interviews, and direct observation to evaluate how climate fluctuations impact those engaged in fishing activities, with analysis performed using MS Excel and SPSS software. The sample consisted of 150 participants from the Kasena Nankana municipality, comprising 80 fishing practitioners and 70 food vendors (including fish traders, kenkey vendors, rice sellers, and fried yam vendors). Findings indicate that fishing practitioners encounter multiple interrelated challenges, with climatic conditions (identified by 42.5% of participants) and economic limitations (noted by 41.3% of participants) representing the primary concerns. These challenges are mutually reinforcing - variable climate patterns decrease fish yields, subsequently diminishing earnings and restricting capacity for equipment upgrades. The interconnected character of these challenges indicates that successful interventions require comprehensive approaches addressing multiple dimensions concurrently. Combining climate adaptation measures, economic assistance programs, and equipment modernization initiatives would prove more beneficial than tackling individual challenges separately.

<p>Research exploring the efficacy of robots in autism therapy has predominantly relied on the Wizard-of-Oz method, where robots execute predetermined behaviours. However, this approach is constrained by its heavy reliance on human intervention. To address this limitation, we introduce a novel deep-fuzzy personalization framework for social robots to enhance adaptability in interactions with autistic children. This framework incorporates a deep learning model called singleshot emotion detector (SED) with a mean average precision of 93% and a fuzzy-based engagement prediction engine, utilizing factors such as scores, IQ levels, and task complexity to estimate the engagement of autistic children during robot interactions. Implemented on the humanoid robot RoCA, our study assesses the impact of this personalization approach on learning outcomes in interactions with Ghanaian autistic children. Statistical analysis, specifically Mann Whitney tests (U=3.0, P=0.012), demonstrates the significant improvement in learning gains associated with RoCA's adoption of the deep fuzzy approach.</p>

At present, prime numbers are an essential part of online security for secure key generation and digital signatures due to their unpredictabil-‎ity and resistance to factorization attacks, which has led to considerable interest in research on distributions of primes, especially prime gaps ‎and hidden patterns. Traditional prime analytical methods lack structural insight at the scale of cryptographic systems. This has led to greater ‎interest in applying machine learning (ML) techniques to prime analysis. However, due to a lack of publicly available high-quality datasets, ‎the evaluation of prime behavior using ML is often impeded. Furthermore, current prime generation techniques tend to become computa‎tionally inefficient when scaled to produce large quantities of high-bit-length prime numbers. In response, this paper proposes a novel generative pipeline, GANLPN, that leverages Generative Adversarial Networks (GANs) combined with the Learning Parity with Noise (LPN) ‎problem to generate bulk primes that are cryptographically secure. In this way, a publicly accessible dataset of 1,115,000 1024-bit primes ‎has been generated. The generated sequences passed all NIST SP800-22 statistical randomness tests with better inference time and throughput. The present work outlines a path for future ML-assisted studies of prime patterns, gaps, distributions, and the presence of weak keys in ‎cryptography.

Contract farming is important for integrating smallholder farmers into agricultural value chains in developing countries. While previous research has explored the impacts of contract farming on welfare and productivity, there remains a gap in understanding how specific contract design attributes influence farmers’ willingness to participate. Existing studies often overlook the heterogeneity of farmer preferences and the interaction between socioeconomic/demographic/institutional factors. This study investigates Ghanaian farmers' preferences for agricultural contract design, examining how socioeconomic, demographic, and institutional willingness to participate in contract farming. A discrete choice experiment was conducted with 279 Ghanaian farmers across four regions. The DCE used a conditional logit model in analyzing farmers' preferences for contract type, pricing mechanism, yield commitments, input support, and partner reliability, and a logit model to identify participation determinants. It offers insights into the dynamics of contract farming by examining farmers' preferences for contract design attributes using a discrete choice experiment. The findings reveal that farmers favor written contracts, quality-based pricing, full yield commitments, limited input support, and openness to new partnerships – underscoring the importance of formalization, autonomy, and market incentives. Importantly, the study highlights that farmers are not a homogeneous group; preferences vary significantly by gender, household size, income, access to extension, and market distance. This study highlights the need for differentiated, farmer-centric contract models that reflect the diverse socioeconomic realities of smallholders. The findings extend contract farming theory by revealing key preference patterns and interaction effects, offering actionable insights for designing flexible, inclusive contracts that improve participation, retention, and long-term sustainability.