The importance of early diagnosis of chronic diseases will help in minimizing disease burden, reduce the outcome of patients, and decrease the cost of healthcare in the long-term. New technologies in the field of Artificial Intelligence (AI) allow applying predictive analytics to diagnose disease risk at an early stage using big data on clinical analysis. In this research, the researchers examine the capability of AI-based predictive models to identify early chronic disease through anonymized el
Sentiment Analysis is important to analyze consumer feedback especially in the social media where large amounts of data are being created every day. The paper explores how BERT (Bidirectional Encoder Representations from Transformers) a state of the art deep learning model may be used to analyze the sentiment of social media posts on consumer products. We use BERT on a customer review case study on Twitter, Instagram, and Facebook of a well-known consumer product. The analysis categorizes the se
Flash floods in steep tropical basins are a result of the interplay of short-duration rainfall extremes, antecedent wetness, relief, drainage connectivity, and land-surface conditions. The present study compares the machine-learning and deep-learning techniques for flood-susceptibility mapping in the Sangu-Matamuhuri River Basin, Bandarban-Cox's Bazar, southeast Bangladesh, using a diverse geospatial and hydrometeorological benchmark. There are 250 labelled samples, 16 static GIS-like predictors
With the increasing sophistication in cyber threat, conventional security mechanisms are in most cases not enough to guard organizations against the emerging risks. Cybersecurity has also gained a lot of strength through the use of artificial intelligence (AI) to detect and respond to threats. Threat detection models based on machine learning, predictive analytics, and automated security operations are AI-driven and allow achieving more precise detection, lowering false positives, and increasing
The perception of autonomous vehicles is based on the real-time and precise detection of objects in various and, in many cases, unfavorable conditions of the environment. This paper provides a comparative analysis of two-stage (Faster R-CNN) detectors, one-stage (YOLOv8,SSD) detectors, and transformer-based (RT-DETR) detectors in terms of accuracy of detection, real-time inference, and their implementation when the environment suffers degradation, on the KITTI dataset and the Cityscapes dataset.
Hyperparameter optimization is an important feature of enhancing the performance of Deep Reinforcement Learning (DRL) algorithms. Although hyperparameter optimization has been addressed in settings involving the traditional Reinforcement Learning (RL), DRL systems are much more complicated in nature, which complicates the task. In this study, the researchers explore the opportunity of using hybrid meta-heuristic algorithms to optimize some of the most important hyperparameters of DRL models: lea
