Short-term wind power forecasting through stacked and bi directional LSTM techniques.

Background: Computational intelligence (CI) based prediction models increase the efficient and effective utilization of resources for wind prediction. However, the traditional recurrent neural networks (RNN) are difficult to train on data having long-term temporal dependencies, thus susceptible to an inherent problem of vanishing gradient. This work proposed a method based on an advanced version of RNN known as long short-term memory (LSTM) architecture, which updates recurrent weights to overcome the vanishing gradient problem. This, in turn, improves training performance. Methods: The RNN model is developed based on stack LSTM and bidirectional LSTM. The parameters like mean absolute error (MAE), standard deviation error (SDE), and root mean squared error (RMSE) are utilized as performance measures for comparison with recent state-of-the-art techniques. Results: Results showed that the proposed technique outperformed the existing techniques in terms of RMSE and MAE against all the used wind farm datasets. Whereas, a reduction in SDE is observed for larger wind farm datasets. The proposed RNN approach performed better than the existing models despite fewer parameters. In addition, the approach requires minimum processing power to achieve compatible results.

The prevalence of prostate cancer in Pakistan: A systematic review and meta-analysis.

Background: Prostate cancer is a significant public health issue, ranking as the second most common cancer and the fifth leading cause of cancer-related deaths in men. In Pakistan, the prevalence of prostate cancer varies significantly across published articles. This study aimed to determine the pooled prevalence of prostate cancer and its associated risk factors in Pakistan. Methods: MEDLINE (via PubMed), Web of Science, Google Scholar, and local databases were searched from inception until March 2023, using key search terms related to the prevalence of prostate cancer. We considered a random-effects meta-analysis to derive the pooled prevalence and relative risks with 95% CIs. Two investigators independently screened articles and performed data extraction and risk of bias analysis. We also conducted meta-regression analysis and stratification to investigate heterogeneity. This study protocol was registered at PROSPERO, number CRD42022376061. Results: Our meta-analysis incorporated 11 articles with a total sample size of 184,384. The overall pooled prevalence of prostate cancer was 5.20% (95% CI: 3.72-6.90%), with substantial heterogeneity among estimates (I2 = 98.5%). The 95% prediction interval of prostate cancer was ranged from 1.74%-10.35%. Subgroup meta-analysis revealed that the highest pooled prevalence of prostate cancer was in Khyber Pakhtunkhwa (8.29%; 95% CI: 6.13-10.74%, n = 1), followed by Punjab (8.09%; 95% CI:7.36-8.86%, n = 3), while the lowest was found in Sindh (3.30%; 95% CI: 2.37-4.38%, n = 5). From 2000 to 2010 to 2011-2023, the prevalence of prostate cancer increased significantly from 3.88% (95% CI: 2.72-5.23%) to 5.80% (95% CI: 3.76-8.24%). Conclusions: Our meta-analysis provides essential insights into the prevalence of prostate cancer in Pakistan, highlighting the need for continued research and interventions to address this pressing health issue.

A Natural Language Processing (NLP) Evaluation on COVID-19 Rumour Dataset Using Deep Learning Techniques.

Context and Background: Since December 2019, the coronavirus (COVID-19) epidemic has sparked considerable alarm among the general community and significantly affected societal attitudes and perceptions. Apart from the disease itself, many people suffer from anxiety and depression due to the disease and the present threat of an outbreak. Due to the fast propagation of the virus and misleading/fake information, the issues of public discourse alter, resulting in significant confusion in certain places. Rumours are unproven facts or stories that propagate and promote sentiments of prejudice, hatred, and fear. Objective. The study's objective is to propose a novel solution to detect fake news using state-of-the-art machines and deep learning models. Furthermore, to analyse which models outperformed in detecting the fake news. Method. In the research study, we adapted a COVID-19 rumours dataset, which incorporates rumours from news websites and tweets, together with information about the rumours. It is important to analyse data utilizing Natural Language Processing (NLP) and Deep Learning (DL) approaches. Based on the accuracy, precision, recall, and the f1 score, we can assess the effectiveness of the ML and DL algorithms. Results. The data adopted from the source (mentioned in the paper) have collected 9200 comments from Google and 34,779 Twitter postings filtered for phrases connected with COVID-19-related fake news. Experiment 1. The dataset was assessed using the following three criteria: veracity, stance, and sentiment. In these terms, we have different labels, and we have applied the DL algorithms separately to each term. We have used different models in the experiment such as (i) LSTM and (ii) Temporal Convolution Networks (TCN). The TCN model has more performance on each measurement parameter in the evaluated results. So, we have used the TCN model for the practical implication for better findings. Experiment 2. In the second experiment, we have used different state-of-the-art deep learning models and algorithms such as (i) Simple RNN; (ii) LSTM + Word Embedding; (iii) Bidirectional + Word Embedding; (iv) LSTM + CNN-1D; and (v) BERT. Furthermore, we have evaluated the performance of these models on all three datasets, e.g., veracity, stance, and sentiment. Based on our second experimental evaluation, the BERT has a superior performance over the other models compared.

Predicting Mental Health of Best Human Capital for Sustainable Organization through Psychological and Personality Health Issues: Shift from Traditional to Novel Machine Learning-Supervised Technique Approach.

Researchers in the past discussed the psychological issue like stress, anxiety, depression, phobias on various forms, and cognitive issues (e.g., positive thinking) together with personality traits on traditional research methodologies. These psychological issues vary from one human to other human based on different personality traits. In this paper, we discussed both psychological issues together with personality traits for predicting the best human capital that is mentally healthy and strong. In this research, we replace the traditional methods of research used in the past for judging the mental health of the society, with the latest artificial intelligence techniques to predict these components for attaining the best human capital. In the past, researchers have point out major flaws in predicting psychological issue and addressing a right solution to the human resource working in organizations of the world. In order to give solution to these issues, we used five different psychological issues pertinent to human beings for accurate prediction of human resource personality that effect the overall performance of the employee. In this regard, a sample of 500 data has been collected to train and test on computer through python for selecting the best model that will outperform all the other models. We used supervised AI techniques like support vector machine linear, support vector machine radial basis function, decision tree model, logistic regression, and neural networks. Results proved that psychological issue data from employee of different organizations are better means for predicting the overall performance based on personality traits than using either of them alone. Overall, the novel traditional techniques predicted that sustainable organization is always subject to the control of psychological illness and polishing the personality traits of their human capital.

Potential Future Directions in Optimization of Students' Performance Prediction System.

Previous studies widely report the optimization of performance predictions to highlight at-risk students and advance the achievement of excellent students. They also have contributions that overlap different fields of research. On the one hand, they have insightful psychological studies, data mining discoveries, and data analysis findings. On the other hand, they produce a variety of performance prediction approaches to assess students' performance during cognitive tasks. However, the synchronization between these studies is still a black box that increases prediction systems' dependency on real-world datasets. It also delays the mathematical modeling of students' emotional attributes. This review paper performs an insightful analysis and thorough literature-based survey to draw a comprehensive picture of potential challenges and prior contributions. The review consists of 1497 publications from 1990 to 2022 (32 years), which reported various opportunities for future performance prediction researchers. First, it evaluates psychological studies, data analysis results, and data mining findings to provide a general picture of the statistical association among students' performance and various influential factors. Second, it critically evaluates new students' performance prediction techniques, modifications in existing techniques, and comprehensive studies based on the comparative analysis. Lastly, future directions and potential pilot projects based on the assumption-based dataset are highlighted to optimize the existing performance prediction systems.

Novel Deep Convolutional Neural Network-Based Contextual Recognition of Arabic Handwritten Scripts.

Offline Arabic Handwriting Recognition (OAHR) has recently become instrumental in the areas of pattern recognition and image processing due to its application in several fields, such as office automation and document processing. However, OAHR continues to face several challenges, including high variability of the Arabic script and its intrinsic characteristics such as cursiveness, ligatures, and diacritics, the unlimited variation in human handwriting, and the lack of large public databases. In this paper, we introduce a novel context-aware model based on deep neural networks to address the challenges of recognizing offline handwritten Arabic text, including isolated digits, characters, and words. Specifically, we propose a supervised Convolutional Neural Network (CNN) model that contextually extracts optimal features and employs batch normalization and dropout regularization parameters. This aims to prevent overfitting and further enhance generalization performance when compared to conventional deep learning models. We employ a number of deep stacked-convolutional layers to design the proposed Deep CNN (DCNN) architecture. The model is extensively evaluated and shown to demonstrate excellent classification accuracy when compared to conventional OAHR approaches on a diverse set of six benchmark databases, including MADBase (Digits), CMATERDB (Digits), HACDB (Characters), SUST-ALT (Digits), SUST-ALT (Characters), and SUST-ALT (Names). A further experimental study is conducted on the benchmark Arabic databases by exploiting transfer learning (TL)-based feature extraction which demonstrates the superiority of our proposed model in relation to state-of-the-art VGGNet-19 and MobileNet pre-trained models. Finally, experiments are conducted to assess comparative generalization capabilities of the models using another language database , specifically the benchmark MNIST English isolated Digits database, which further confirm the superiority of our proposed DCNN model.