Since rising worldwide energy consumption is anticipated with increasing rapid industrialization and urbanization, green energy sources have become the ineluctable choice among energy engineers, power engineers, and researchers for carbon-free and sustainable electric power generation. By integrating several energy sources, a hybrid renewable and sustainable power supply system (HRSPSS) has been created to solve the global warming problem. HRSPSS aims to develop contemporary electricity grids that benefit society, the environment, and the economy. However, there is a need for thorough assessment of these complex HRSPSSs for making the most use of renewable energy potential and carefully crafting suitable solutions. This paper provides a thorough investigation of the most effective methods for sizing, optimizing, controlling, and managing energy, as well as how to combine different renewable energy sources to create a hybrid sustainable power supply system. Information on several software simulation tools and optimization methods that have been used to support HRSPSS development, research, and planning is presented in this study. Additionally, this study covers energy management and control strategies that have been used to ensure efficient and optimal operation of HRSPSS. Furthermore, this article presents an extensive comparison among various strategies utilized in each area (sizing, optimizing, controlling, and managing energy) to provide conclusive remarks on the suitable strategies for respective applications. The outcome of this study will help various stakeholders in the energy sector to make appropriate decisions during the design, development, and implementation phases of a hybrid sustainable power supply system.
As the transition to Electric Vehicles (EVs) accelerates, enhancing the resilience of electrical systems becomes increasingly crucial. A key component in EVs is the Power Electronic Converter (PEC), which not only powers the electric motors but also reconfigures the grid charging of the battery bank. This paper introduces a fault detection system specifically designed for a prevalent type of charger used in EVs. The system aims to identify faults that may lead to malfunctions during the operation of the onboard electric charger, thereby enabling a supervisory system to execute corrective measures and maintain uninterrupted charging operations. The proposed fault detection method leverages a Machine Learning (ML) technique known as a classification algorithm. The system is trained using grid-side Total Harmonic Distortion (THD) and load resistance values to classify potential faults accurately. Extensive testing demonstrates that the proposed system achieves a fault prediction accuracy of around 94.59 %, showcasing superior performance in terms of training and execution times as well as overall accuracy. This study underscores the effectiveness of integrating advanced ML techniques in enhancing the reliability and efficiency of EV charging systems, thus contributing to a smoother and faster transition to electric mobility.
In the field of weather, forecasting is a critical application that has long been considered one of the world’s most difficult scientific and technical issues. Data mining is as the practice of discovering previously unknown and practical information and knowledge that is embedded in enormous volumes of unclear, noisy, random, and incomplete data. In this study, however, an examination of many common data mining techniques for weather prediction has been offered. Different type of data mining techniques has been investigate. Also, based on that, weather prediction comparison using different data mining approaches has been investigated. Nevertheless, methodologies like data cleaning, data integration, data selection, data transformation, etc. has been discussed for reaching the best solution of predicting weather by using data mining. Finally, this study illustrates how k-means and decision trees are the most appropriate data mining methods for this use case.
This research presents the development of a portable arm rehabilitation device designed to continuously monitor and enhance rehabilitation activities. The device incorporates flex sensors, force-sensitive resistors, and accelerometers interfaced with an ESP32 microcontroller to collect data on arm movements. This data is crucial for therapists to fine-tune treatment plans and provide patients with an effective home-based rehabilitation solution. Recent findings have shown the potential of home-based rehabilitation, yet existing technologies are often costly and complex to operate independently. The device aims to bridge this gap by offering a user-friendly and affordable solution. The system integrates various sensors, including flex sensors, force-sensitive resistors, and accelerometers, which are interfaced with an Arduino microcontroller. These sensors capture data related to arm movements, which is essential for therapists to tailor treatment plans and for patients to track their progress. The device aims to bridge the gap between costly and complex rehabilitation technologies and the need for accessible, home-based solutions. The study's novelty lies in its integration of sensor technology into a smart glove and its commitment to providing an affordable and effective rehabilitation solution. The continuous monitoring capabilities of the device offer valuable insights into patients' progress, improving the quality of rehabilitation programs. This work aligns with recent advancements in wearable technology and sensor systems for healthcare applications, emphasizing the importance of accessible rehabilitation solutions.
8 May 2023 in AIUB Journal of Science and Engineering (AJSE)
Bangladesh is highly affected by climate change scenarios notably floods due to its location on the world map in the South Asian region. Besides due to monsoon rains and high upstream rainfall in several areas eventually turn into floods. Thus, early flood forecasting might save human lives as well as agriculture crops. In this paper, we have applied different machine learning classifier models (Decision tree, Naive bayes, k-NN and Random forest) with a view to predicting the occurrence of flood. RapidMiner tool has been used extensively to perform data preparation, decision tree model generation, cross-validation, model selection and optimization of the model parameters. It is seen that the decision tree model has performed well by achieving an accuracy of 94.23% which is further optimized to reach 94.68%. Feature Selection using ‘correlation matrix’ is also a good aspect of this work by which we have achieved a good accuracy.
This study aims to identify human movement activities using machine learning, focusing on a novel ensemble approach. The objectives are twofold: to apply a new machine learning method for activity recognition and to outperform recent approaches in accuracy. A standard dataset from Kaggle contained six activities: standing, sitting, lying, walking, walking downstairs, and walking upstairs. The study used an SVM and Logistic Regression ensemble alongside other standard classifiers. The proposed ensemble achieved an accuracy of 95.45% on the test data, surpassing other models. This research shows the potential of the ensemble approach for accurate human movement identification with potential uses in various domains.