This chapter examines the evolution of predictive microbiology from classical growth models to modern digital predictive microbiology and positions predictive analytics as the critical link between microbial data ecosystems and evidence-based decision support. It reviews the foundations of digital predictive microbiology, including data acquisition, integration, model development, validation, uncertainty analysis, and decision translation, and synthesizes major modeling approaches encompassing mechanistic, statistical, Bayesian, machine learning, hybrid, and digital twin frameworks. The chapter further explores the integration of quantitative microbial risk assessment with AI-enabled predictive systems and highlights applications across food safety, healthcare, wastewater surveillance, environmental monitoring, agriculture, industrial biotechnology, and One Health. Ethical governance, model transparency, explainable AI, and regulatory considerations are discussed as essential requirements for responsible implementation.
This research examined the water quality in the Asese/Mowe Industrial Area of Ogun State, Nigeria. Twenty (20) water samples comprising both surface and groundwater sources were obtained from industrial zones and subjected to comprehensive physicochemical analysis using standard procedures. The analytical parameters examined encompassed pH levels, electrical conductivity (EC), total dissolved solids (TDS), dissolved oxygen (DO), biological oxygen demand (BOD), chemical oxygen demand (COD), and principal anionic constituents (chloride (Cl⁻), sulphate (SO42⁻), and nitrate (NO3⁻)). Surface and groundwater quality analysis was evaluated using water quality index (WQI). 14 out of the evaluated 20 samples had pH below the minimum acceptable limit of 6.5, indicating that the water in many locations is slightly acidic. The COD values varied between 3.99 and 12.04 mg/l, with a mean value of 7.09 (± 1.88) mg/l. SW1 exhibits a COD level of 12.04 mg/L, which fails to comply with the required COD standards and consequently renders it unsuitable for drinking water consumption based on COD criteria. Results show that the WQI values for the 20 samples ranged between 6.83 and 106.73 reflecting noticeable variation in water quality across different sampling points. 45
Recent advances in machine and deep learning have paved the way for automated quality control in injection molding. However, existing approaches still face challenges such as insufficient performance evaluations, scarce training data, and limited generalization. In this study, a comparative evaluation of commonly used pretrained Convolutional Neural Networks, including InceptionV3, ResNet-101, ResNet-50, and VGG16, for defect detection was carried out. It was shown that InceptionV3 outperformed the other models in test accuracy and convergence behavior, under consistent hyperparameter settings and fine-tuning strategies. Building on this, Squeeze-and-Excitation (SE) and Convolutional Block Attention Module (CBAM) were integrated into InceptionV3, forming InceptionV3-SE-CBAM, to enhance feature representation. The proposed framework was tested on three diverse injection molding datasets to demonstrate generalized application and industrial adaptability. Compared to the baseline InceptionV3, the InceptionV3-SE-CBAM achieved accuracy gains in excess of 23.9
We examine women's dominance in Nigerian journalism classrooms despite their lack of commensurate representation in newsrooms. Drawing on 27 in-depth interviews with female students, we find that journalism is often pursued as a fallback option, limiting initial motivation. Within training institutions, perceptions of poor teaching, lack of practical training, and toxic learning environments appear to contribute to disengagement from the practice. Patriarchal norms, including assumptions about men's provider role and privileging men's authority, shape their perception of these discouraging lessons. The findings compound existing pipeline explanations for this disparity, with implications for scholarship on gender equity, journalism pedagogy, and practice.
PURPOSE:The health and well-being of young adult building artisans are germane because of their critical role in infrastructure development. There is a perceived increase and paucity of studies regarding young adult building artisans' involvement in illicit substances, which threatens the achievement of Sustainable Development Goals (SDGs) 3 and 8. This study investigated the underlying causes and recommended feasible measures to prevent or mitigate the use of illicit substances among young adult artisans on construction sites in Nigeria, and, by extension, to improve the achievement of Goals 3 and 8. DESIGN/METHODOLOGY/APPROACH:This research employs a face-to-face interview to collect data in Lagos and Abuja, Nigeria. FINDINGS:Findings reveal that there is a prevalent issue of increasing young adult building artisans' illicit substance intake on building sites. This poses a significant threat to occupational health (SDG 3) and workplace safety (SDG 8). Findings also identified 17 underlying causes, including a lack of awareness among artisans, a low educational background and lax safety and management policies. ORIGINALITY/VALUE:This research contributes to the existing literature on preventing or mitigating illicit substance use among young adult building artisans. It also recognises that preventive or mitigative measures can be useful for mental health stability and, by extension, for achieving the SDGs.
