International Journal of Innovative Research and Scientific Studies

AI-mediated pronunciation training: Vietnamese EFL learners' perceptions of ELSA speak

2026-03-03T04:09:30-06:00

This study examines how first-year English majors at Hanoi Metropolitan University, Vietnam perceive ELSA Speak as a pronunciation learning tool, with a focus on learner autonomy, technological affordances, and institutional constraints within mobile-assisted language learning (MALL). Using a convergent parallel mixed-method design, the study collected quantitative data from 110 participants through a structured survey (Cronbach's alpha = 0.87) and qualitative data from semi-structured interviews with 24 purposively selected participants. Data were analysed using SPSS 26.0, thematic analysis following Braun and Clarke [1] and NVivo 12, within a theoretical framework integrating the Technology Acceptance Model and Self-Determination Theory. 77.3% percent of the participants found ELSA Speak effective or highly effective for improving their pronunciation. Learners reported increased confidence (81.8%) and motivation (68.2%), and they considered instant phoneme feedback the most valuable feature (M = 4.2, SD = 0.7). Three primary constraints were consistently cited: inadequate contextual practice (forty point nine percent), the expense associated with premium functionalities (36.4%), and connectivity issues (31.8%). Qualitative examination identified accent bias within speech recognition as a prevalent concern, specifically impacting the precision of feedback for English spoken with a Vietnamese accent. These observations indicate that ELSA Speak facilitates pronunciation practice and learner autonomy, despite accent bias, an over-dependence on automated feedback, and a restricted emphasis on suprasegmental features representing notable limitations. Therefore, educators should use ELSA Speak in blended learning environments that combine AI tools with traditional teaching methods. At the same time, institutions should address accessibility issues related to cost and infrastructure.

Water use optimization in fish farms: Efficient strategies to reduce environmental impact

2026-03-04T04:52:00-06:00

Aquaculture has now become an important agricultural activity in meeting global food needs. However, the intensification of this activity places daily pressure on water resources and aquatic ecosystems. The goal of this study was to find efficient ways to optimize water use in fish farms, helping to reduce their environmental impact. We did a literature review using systematic mapping that combined analysis of scientific databases with defined inclusion and exclusion criteria. The results showed that there is a growing interest in the search for technologies that enable water savings and efficient use in the aquaculture chain, notably recirculation, biofloc, aquaponics, and biofiltration, which can reduce water consumption and minimize the pollutant load in water. It is concluded that the adoption of alternatives for water resource management in aquaculture is a viable path that contributes to the sustainability and competitiveness of this economic activity.

Knowledge management and innovation in SMEs: Case study in Lubango city/Angola

2026-03-05T22:24:49-06:00

This study investigates the relationship between knowledge management processes and organizational innovation in Small and Medium-sized Enterprises (SMEs) operating in the city of Lubango, as well as the associated implications and challenges for organizational performance. A quantitative research design was adopted, using data collected through a structured questionnaire administered to 50 managers. The findings from the regression analysis reveal that Organizational Innovation (β = 0.505) and Process Innovation (β = 0.341) exert positive and statistically significant effects on overall firm performance. Conversely, Product Innovation does not exhibit a statistically significant impact when examined simultaneously with the other explanatory variables. The model explains 64.2% of the variance in performance (adjusted R² = 0.642), with homoscedastic, independent residuals and no problematic multicollinearity (VIF < 3). The results indicate that, within the business context of Lubango, the attainment of sustainable competitive advantage by local SMEs is more closely related to the optimization of internal organizational structures and operational efficiency than to the introduction of new products. Managers should prioritize knowledge sharing and application, organizational design, managerial training, and process optimization.

Emotion recognition training with virtual reality in schizophrenia: A case series study

2026-03-05T22:29:31-06:00

The purpose of the study was to assess the tolerability and acceptability, and to explore the preliminary efficacy of an 8-session emotion-recognition training using virtual reality (VR-ER) through the software VR-Tóol in three patients within the schizophrenia spectrum. Methodology: A single case AB design was employed. Prior to the intervention, three emotion recognition (ER) baseline measurements were collected, and three additional measurements were obtained during the intervention. Pre- and post-intervention measures of ER, symptomatology, neurocognition, apathy, depression, and functionality were obtained by independent researchers. For quantitative analysis of the baseline measures, the Conservative Dual-Criterion method, two-standard deviation band, and Non-overlap of all Pairs were employed. For the pre- and post-intervention measures, the reliable change index was used. Findings: None to minimal cybersickness symptoms were observed during the intervention. Patients reported motivation toward the intervention and good levels of perceived effectiveness. Regarding the intervention efficacy, we found clinical changes in ER, neurocognition, and functionality. Conclusions: The present study offers preliminary evidence of the acceptability and efficacy of a targeted VR-ER intervention in patients within the schizophrenia spectrum. Practical implications: These findings underscore the practical efficacy of virtual reality in social cognition interventions. VR-Tóol is a promising technological tool that has the potential to serve as a rehabilitation aid for sociocognitive processes in psychiatric conditions, such as schizophrenia.

Markov-based algorithms for wireless sensor network: Theoretical insights and python implementation

2026-03-07T05:37:46-06:00

The study concentrates on improving the dependability and operational efficacy of LoRa-based Wireless Sensor Networks (WSNs), which are extensively utilized in IoT applications, especially for long-range private networks. It seeks to deal with the problems that arise when a single node or communication line fails, which can have a big effect on network performance. The research utilizes a Markovian matrix theoretical framework to examine and simulate the behavior of LoRa-based Wireless Sensor Networks (WSNs), incorporating states such as Sleep (S), Idle (I), Transmit (T), and Receive (R) mode. A Python software program was created to put this model into action, allowing for testing and simulation with 50 fake data sets. The method stresses that the network should always be running, that sensor nodes should be replaced quickly, and that the network should be able to handle failures of individual nodes. The simulations indicate that using the Markov chain model in conjunction with detailed step-by-step math computation may yield a more accurate analysis of the data sets. The methodology also helps you evaluate protocols, change control, look at scalability, and make informed choices about how to build a network. This work offers practical benefits for the design, deployment, and maintenance of LoRa-based WSNs in real-world IoT scenarios. It supports network administrators and engineers in predicting power consumption, designing resilient protocols, scaling networks efficiently, and implementing adaptive control measures to ensure continuous and dependable operation. The integration of Markov chain mathematical modeling with Python-based simulation provides a robust solution for ensuring reliable operation of LoRa-based WSNs. The approach mitigates the impact of node failures, supports rapid recovery, and maintains network integrity.

Diversity and inclusion: A strong foundation for learning agility and culture fit in enhancing a successful employee experience through performance recognition

2026-03-10T03:37:04-05:00

This study examines the role of Diversity and Inclusion (DI) in supporting Learning Agility (LA) and Culture Fit (CF), as well as their influence on Employee Experience (EE) and Performance Recognition (PR) within organizations in Malang. The research gap lies in the limited number of empirical studies on the implementation of DI in local contexts, while most of the existing literature predominantly focuses on large corporations. Accordingly, this study is expected to provide practical contributions for organizations in fostering an inclusive work culture, enhancing the quality of human resources, and promoting both employee performance and satisfaction. The findings of the study reveal several key relationships among the examined variables. First, Culture Fit is found to have a significant influence on Performance Recognition. Second, Diversity and Inclusion significantly influence Culture Fit, while also exerting a positive effect on Employee Experience and Performance Recognition. Furthermore, Employee Experience demonstrates a significant effect on Performance Recognition. Third, Learning Agility is shown to influence both Culture Fit and Employee Experience, although it does not directly affect Performance Recognition. However, the analysis also uncovers several indirect effects: Diversity and Inclusion influence Performance Recognition through Culture Fit, Learning Agility influences Performance Recognition through Culture Fit, Diversity and Inclusion influence Performance Recognition through Employee Experience, and Learning Agility influences Performance Recognition through Employee Experience. Overall, this research makes a substantial contribution to the advancement of human resource management theory and practice, particularly in relation to the implementation of Diversity and Inclusion and the development of Learning Agility within organizations. By integrating these elements, this study emphasizes the importance of a comprehensive approach to achieving organizational goals more efficiently while remaining responsive to the needs and expectations of individuals in the workplace.

Tax–trade nexus in Nigeria: An empirical analysis of oil and non-oil imports and exports

2026-03-14T01:43:11-05:00

This study examined the impact of taxation on oil and non-oil trade flows in Nigeria between 2011Q1 and 2024Q4. The study employs the Autoregressive Distributed Lag (ARDL) modelling framework to analyse the short- and long-run effects of key tax variables, customs duties (CDT), value-added tax (VAT), and corporate income tax (CIT), on oil and non-oil trade flows in Nigeria. The results reveal that positive shocks to customs duties significantly increase oil imports and non-oil exports in the short run. In contrast, VAT demonstrates limited influence across the different trade categories. Corporate income tax is found to stimulate non-oil exports in the short run but exerts minimal effects on imports. Exchange rate depreciation reduces both non-oil imports and exports. In the long run, customs duties remain a significant driver of trade flows, while both corporate income tax and VAT tend to constrain trade activities. The findings highlight the heterogeneous effects of taxation on different components of trade in Nigeria. While certain tax instruments, particularly customs duties, can stimulate trade flows, others may impose constraints that affect the performance of the external sector over time. The study suggests that policymakers should design tax strategies that balance revenue mobilisation with trade promotion. In particular, tax policies should account for sectoral differences between oil and non-oil trade, while also considering the interactions between taxation, exchange rate dynamics, and investment conditions to ensure sustained external sector stability and diversification of Nigeria’s trade base.

Precision agriculture for smallholder farmers: Maximizing economics productivity using a machine learning-based water recommendation system

2026-03-17T05:22:54-05:00

This study explores how smallholder farmers in various communities can economically optimize productivity, connectivity, and efficiency using precision agricultural technologies, particularly and sensors. The study can empower many small scale farmers by demonstrating customized applications of precision agriculture tools, thus boosting their ability to maximize resource utilization, reducing risks, and increasing yields. Furthermore, this study developed a machine learning (ML) decision-making system to improve crop yield for smallholder farmers economically in rural South Africa. This system specifically optimises irrigation by detecting soil moisture anomalies and providing recommendations to maintain optimalsoil moisture levels. The optimal range was set for the range of 70 to 80%. The system was trained and modelled using several parameters of soil moisture humidity, atmospheric temperature, soil temperature, and soil moisture. A comparison was carried out using MLmodel and Logistic regression, XGBoost, CatBoost, Gradient Boosting and Support vector 13 machine (SVM). The metrics used were accuracy, F1 Score, Recall, and Precision. The results showed 4 that the XGBoost model performed better than the other four models5 with an accuracy of 0.73, an F1 Score of 0.64, and a recall of 0.73. The Gradient Boosting16 model had the 2nd best result with a precision of 0.79. The findings demonstrated that optimizing irrigation systems, enhanced crop yield could be achieved with better stability.

An explainable hybrid machine learning model for data-driven assessment and enhancement of program learning outcomes in higher education

2026-03-23T23:48:43-05:00

The purpose of this study is to develop and validate an explainable hybrid machine learning framework for accurately assessing and enhancing Program Learning Outcomes (PLOs) in higher education. The study aims to overcome the limitations of conventional manual or heuristic evaluation methods by leveraging data-driven predictive analytics to identify key factors influencing student achievement. A stacked ensemble learning architecture is proposed, combining multiple gradient boosting and tree-based algorithms: LightGBM, XGBoost, CatBoost, Gradient Boosting, and Decision Tree, under a multinomial Logistic Regression meta-learner. The model was trained and tested on real academic data collected from the University of Tabuk, Saudi Arabia, incorporating academic, behavioral, and demographic variables. Comprehensive preprocessing, stratified k fold cross validation, and grid search optimization were applied to enhance robustness and generalization. SHapley Additive exPlanations (SHAP) were used to interpret model outputs and determine the relative importance of predictors. The hybrid model achieved a micro average ROC AUC of 0.998, along with consistently high precision, recall, and F1 scores across all grade categories (A–F). SHAP analysis revealed that Total Score, Project Score, and Final Score were the strongest predictors of PLO attainment, offering a clear insight into the learning dimensions that contribute most to academic success. Results confirm that the proposed hybrid ensemble outperforms conventional single model and deep learning approaches in both predictive precision and interpretability. By combining accuracy with transparency, the model serves as a valid analytical tool for institutional quality assurance and outcome based education. This framework enables educators and program evaluators to make data driven, evidence based decisions for early identification of at risk students, curriculum refinement, and continuous improvement of teaching strategies. It also provides a replicable methodology for integrating explainable AI into academic performance assessment in higher education institutions.