Bangladesh University (BU) (Bengali: বাংলাদেশ বিশ্ববিদ্যালয়) is a non-profit, private university. Its main campus is located near the Jatiyo Sangshad Bhaban in Dhaka, Bangladesh. The university was established in 2001 under the Private University Act 1992. The university's founder was Quazi Azher Ali, who served as first vice chancellor of the university from 2001 to 2009.
The sustained expansion of the world’s population has led to a remarkable escalation in renewable energy consumption as global economies adopt green energy systems; therefore, high-fidelity renewable energy consumption forecasting emerges as a crucial factor for efficient energy management and sustainable economic development. This study proposes a hybrid framework for forecasting renewable energy consumption. Machine learning (ML) predictive model integrated statistical models such as simple exponential smoothing (SES), the holt-winters (HW), and the autoregressive integrated moving average (ARIMA) model to form the hybrid framework. The explainable artificial intelligence (XAI) interprets the best predictive model’s feature contributions. The developed forecasting models were evaluated on a hold-out test set and validated across a 24-month future forecast period, along with comparative plots and metrics. The proposed system demonstrates 2.68
Heart disease continues to pose a critical worldwide health issue, more specifically in areas with insufficient access to healthcare infrastructure and diagnostic systems. Conventional diagnostic approaches often fall short in accurately detecting and managing heart disease risks, resulting in unfavorable outcomes. Machine learning presents a powerful means to boost the precision and reliability of cardiovascular disease prognosis and diagnosis. In this research, we introduced a unified approach incorporating classification techniques for detecting heart disease and regression techniques for forecasting associated risks. The analysis utilized the dataset, named Heart Disease, containing 1,035 instances. To mitigate the problem of data disproportion, the SMOTE was implemented, producing 100,000 additional synthetic samples. Evaluation metrics such as F1-score, recall, precision, accuracy, MAE, RMSE, MSE, and R2 were adopted to evaluate the performance of the models. Among the classification algorithms, Random Forest delivered the most notable results, attaining an accuracy of 0.972 on actual data and 0.976 on artificially generated data. For prediction modeling, for both synthetic and real samples, linear regression produced the best R2 values of 0.992 and 0.984, respectively, along with the least amount of measurement errors. Furthermore, Explainable AI methods were utilized to improve the comprehensibility of the model outcomes. This paper emphasizes the transformative capabilities of machine learning for diagnosing cardiovascular disease and estimating risk levels, thereby supporting timely interventions and enhancing clinical settings.
This study presents a detailed investigation of the two-dimensional magnetohydrodynamic (MHD) flow of a Casson hybrid nanofluid with chemical reactions through a perpendicular porous channel under sinusoidal boundary conditions. The introduction of periodic MHD effects and oscillatory wall motion represents the key novelty of this work. The governing nonlinear partial differential equations are transformed into non-dimensional form and solved using a hybrid analytical–numerical approach, with stability and convergence analyses confirming the reliability of the solution. Flow and heat transfer characteristics are analyzed through streamline and isotherm visualizations. The results reveal that the Grashof number and heat source parameter enhance skin friction, while higher Prandtl number, magnetic parameter, porosity, and chemical reaction rate suppress it. Notably, a 25% reduction in velocity is observed as the magnetic parameter increases from 1 to 5, with similar trends evident for other parameters. The findings exhibit strong agreement with existing studies and highlight the model’s practical relevance to biomedical fluid transport, thermal management in electronic systems, and various industrial and manufacturing applications.
This research introduces a quantum machine learning (QML) approach for predicting heart disease (HD). The method combines preprocessing of data with quantum feature map (QFM) and quantum classification techniques. In the method, clinical data of HD are preprocessed, and then features are optimized using principal component analysis (PCA). After that, the resulting features are encoded into quantum states with five different QFM methods, namely angle encoding (AE), amplitude encoding (AmE), basis encoding (BE), Pauli encoding (PE), and ZZ feature map (ZZFM). Finally, four quantum classifiers, such as quantum support vector machine (QSVM), quantum k-nearest neighbor (QKNN), quantum random forest (QRF), and variational quantum circuit (VQC), are evaluated to predict the HD from the encoded states. Experimental results show that QSVM with AE achieved the best performance, with an overall accuracy of 90.26%, specificity of 83.42%, sensitivity of 92.16%, precision of 88.89%, F1-score of 89.68%, and kappa value of 0.7608. These results are superior to those from classical state-of-the-art methods. This research finding suggests QML methods can capture complex nonlinear relationships in clinical data effectively and thus improve diagnostic reliability.
The growing number of machine learning models deployed to dynamic and real-world systems creates the need to be constantly adapted to changing data distributions, concept drift, and operational needs. The conventional paradigms of the traditional methods of static learning do not perform well as time goes on because they do not generalize under different conditions after training. In order to overcome these issues, the paper will present a Self-Optimizing Meta-Learning Framework of Continuous Model Adaptation, which brings together meta-learning, adaptive optimization, and feedbackdriven learning to allow autonomous model evolution. The framework proposed builds upon meta-learning to learn transferable knowledge in tasks, and therefore, gain access to new data by adapting very fast with limited retraining. A selfoptimization module is an adaptive optimizer that optimizes the model parameters and hyperparameters through reinforcement learning and gradient-based methods, and a continuous monitoring layer identifies any change in distribution and initiates adaptive update. Moreover, the framework presents a memory-augmented learning element to store the historical knowledge and avoid disastrous forgetting. Experimental tests on standardized data show that adaptability, convergence rate and long-term predictive accuracy improve significantly over traditional and state-of-the-art adaptive learning methods. The findings indicate that the framework is applicable in real-time analytics, intelligent systems, and large-scale data-driven decision-making due to its efficiency in adapting models in the non-stationary environment in a robust, scalable and autonomous manner.
