Attention-Based Models for Multivariate Time Series Forecasting: Multi-step Solar Irradiation Prediction.

Bangladesh's subtropical climate with an abundance of sunlight throughout the greater portion of the year results in increased effectiveness of solar panels. Solar irradiance forecasting is an essential aspect of grid-connected photovoltaic systems to efficiently manage solar power's variation and uncertainty and to assist in balancing power supply and demand. This is why it is essential to forecast solar irradiation accurately. Many meteorological factors influence solar irradiation, which has a high degree of fluctuation and uncertainty. Predicting solar irradiance multiple steps ahead makes it difficult for forecasting models to capture long-term sequential relationships. Attention-based models are widely used in the field of Natural Language Processing for their ability to learn long-term dependencies within sequential data. In this paper, our aim is to present an attention-based model framework for multivariate time series forecasting. Using data from two different locations in Bangladesh with a resolution of 30 min, the Attention-based encoder-decoder, Transformer, and Temporal Fusion Transformer (TFT) models are trained and tested to predict over 24 steps ahead and compared with other forecasting models. According to our findings, adding the attention mechanism significantly increased prediction accuracy and TFT has shown to be more precise than the rest of the algorithms in terms of accuracy and robustness. The obtained mean square error (MSE), the mean absolute error (MAE), and the coefficient of determination (R2) values for TFT are 0.151, 0.212, and 0.815, respectively. In comparison to the benchmark and sequential models (including the Naive, MLP, and Encoder-Decoder models), TFT has a reduction in the MSE and MAE of 8.4-47.9% and 6.1-22.3%, respectively, while R2 is raised by 2.13-26.16%. The ability to incorporate long-distance dependency increases the predictive power of attention models.

Impact of mobile connectivity on students' wellbeing: Detecting learners' depression using machine learning algorithms.

Depression is a psychological state of mind that often influences a person in an unfavorable manner. While it can occur in people of all ages, students are especially vulnerable to it throughout their academic careers. Beginning in 2020, the COVID-19 epidemic caused major problems in people's lives by driving them into quarantine and forcing them to be connected continually with mobile devices, such that mobile connectivity became the new norm during the pandemic and beyond. This situation is further accelerated for students as universities move towards a blended learning mode. In these circumstances, monitoring student mental health in terms of mobile and Internet connectivity is crucial for their wellbeing. This study focuses on students attending an International University of Bangladesh to investigate their mental health due to their continual use of mobile devices (e.g., smartphones, tablets, laptops etc.). A cross-sectional survey method was employed to collect data from 444 participants. Following the exploratory data analysis, eight machine learning (ML) algorithms were used to develop an automated normal-to-extreme severe depression identification and classification system. When the automated detection was incorporated with feature selection such as Chi-square test and Recursive Feature Elimination (RFE), about 3 to 5% increase in accuracy was observed by the method. Similarly, a 5 to 15% increase in accuracy has been observed when a feature extraction method such as Principal Component Analysis (PCA) was performed. Also, the SparsePCA feature extraction technique in combination with the CatBoost classifier showed the best results in terms of accuracy, F1-score, and ROC-AUC. The data analysis revealed no sign of depression in about 44% of the total participants. About 25% of students showed mild-to-moderate and 31% of students showed severe-to-extreme signs of depression. The results suggest that ML models, incorporating a proper feature engineering method can serve adequately in multi-stage depression detection among the students. This model might be utilized in other disciplines for detecting early signs of depression among people.

Analyzing Perceived Psychological and Social Stress of University Students: A Machine Learning Approach.

The COVID-19 pandemic has worsened the psychological and social stress levels of university students due to physical illness, enhanced dependence on mobile devices and internet, a lack of social activities, and home confinement. Therefore, early stress detection is crucial for their successful academic performance and mental well-being. The advent of machine learning (ML)-based prediction models can have a crucial impact in predicting stress at its early stages and taking necessary steps for the well-being of individuals. This study aims to develop a reliable machine learning-based prediction model for perceived stress prediction and validate the model using real-world data collected through an online survey among 444 university students from different ethnicity. The machine learning models were built using supervised machine learning algorithms. Principal Component Analysis (PCA) and the chi-squared test were employed as feature reduction techniques. Moreover, Grid Search Cross-Validation (GSCV) and Genetic Algorithm (GA) were employed for hyperparameter optimization (HPO). According to the findings, around 11.26% of individuals were identified with high levels of social stress. In comparison, approximately 24.10% of people were found to be suffering from extremely high psychological stress, which is quite alarming for students' mental health. Furthermore, the prediction results of the ML models demonstrated the most remarkable accuracy (80.5%), precision (1.000), F1 score (0.890), and recall value (0.826). The Multilayer Perceptron model was shown to have the maximum accuracy when combined with PCA as a feature reduction approach and GSCV for HPO. The convenience sampling technique used in this study only considers self-reported data, which may have biased results and lack generalizability. Future research should consider a large sample of data and focus on tracking long-term impacts with coping strategies and interventions. The results of this study can be used to develop strategies to mitigate adverse effects of the overuse of mobile devices and promote student well-being during pandemics and other stressful situations.

Rabies: Perils and Prevention, an Insight into Practices and Perception in Residents of Pakistan

Background: There is a sheer lack of knowledge in treating rabies in Pakistan. To decrease the number of victims every year, immunization and awareness programs are the basic necessities of Pakistani population. The aim of this study was to highlight the lack of learning strategies and how to overcome this problem, so as to eliminate rabies. Methods: This cross-sectional study was conducted on 692 respondents, aged 8-50 years, in Karachi city of Pakistan from January 2022 to June 2022. The study was based on demographic characteristics and basic knowledge of rabies, mode of transmission, clinical signs, and range of animal host species. Binary logistic regression analysis was performed to know the risk factor of rabies among different age groups, marital status, occupation, etc. Results: Results revealed that all the age groups were at risk of the wrong knowledge about rabies, odds = 1.182 and odds = 1.775 for 20-30 and 31-40 years of age, respectively; however, 31-40 years were at the high risk of showing odds=3.597 (95% C.I 1.621-7.983). The correlation of occupation was also checked with rabies knowledge. Only doctors (odds = 1.396) and students (odds = 1.955) showed their unawareness about rabies. Conclusion: This study highlights the grave situation that holds the country in the form of rabies. Through this study we aspire to raise awareness regarding the transmission, spread, and control of rabies

Employment of Ensemble Machine Learning Methods for Human Activity Recognition.

The endeavor to detect human activities and behaviors is targeted as a real-time detection mechanism that tends to predict the form of human motions and actions. Though sensors like accelerometer and gyroscopes are noticeable in human motion detection, categorizing unique and individual human gestures require software-based assistance. With the widespread implementation of machine learning algorithms, human actions can be distinguished into multiple classes. Several state-of-the-art machine learning algorithms can be applied to this specified field which will give suitable outcomes, yet due to the bulk of the dataset, complexity can be made apparent, which will reduce the efficiency of the model. In our proposed research, ensemble learning methods have been established by assembling several trained and tuned machine learning models. The adopted dataset for the model has been preprocessed through PCA (principal component analysis), SMOTE oversampling (synthetic minority oversampling technique), and K-means clustering, which reduced the dataset to essentials, keeping the weight of the features intact and reducing complexity. Maximum accuracy of 99.36% was achieved from both stacking and voting ensemble methods.

Survival Prediction of Children Undergoing Hematopoietic Stem Cell Transplantation Using Different Machine Learning Classifiers by Performing Chi-Square Test and Hyperparameter Optimization: A Retrospective Analysis.

Bone marrow transplant (BMT) is an effective surgical treatment for bone marrow-related disorders. However, several associated risk factors can impair long-term survival after BMT. Machine learning (ML) technologies have been proven useful in survival prediction of BMT receivers along with the influences that limit their resilience. In this study, an efficient classification model predicting the survival of children undergoing BMT is presented using a public dataset. Several supervised ML methods were investigated in this regard with an 80-20 train-test split ratio. To ensure prediction with minimal time and resources, only the top 11 out of the 59 dataset features were considered using Chi-square feature selection method. Furthermore, hyperparameter optimization (HPO) using the grid search cross-validation (GSCV) technique was adopted to increase the accuracy of prediction. Four experiments were conducted utilizing a combination of default and optimized hyperparameters on the original and reduced datasets. Our investigation revealed that the top 11 features of HPO had the same prediction accuracy (94.73%) as the entire dataset with default parameters, however, requiring minimal time and resources. Hence, the proposed approach may aid in the development of a computer-aided diagnostic system with satisfactory accuracy and minimal computation time by utilizing medical data records.