Search

Nowadays, deep learning models are used to summarize the large volume of text data to understand its intent effectively. Processing huge amounts of data can lead to an Information overload, where the models may generate text summaries that miss out on the important information of actual text content. Such problems in business document summaries can impact progressive business growth. This study employs a dataset comprising business articles sourced from BBC News to conduct an extensive comparative analysis of three prominent text summarization algorithms: Bidirectional and Auto-Regressive Transformers, Text-to-Text Transfer Transformer, and Pre-training with Extracted Gap-sentences for Abstractive Summarization, within the domain of business news summarization. The primary objective is to assess the accuracy of these models in generating concise and coherent summaries, utilizing ROUGE and METEOR scores as the benchmark for evaluation. Each model's proficiency in distilling business narratives while retaining crucial insights is carefully examined. This study analyzes the summaries generated and compares them with the already existing summaries. From the result analysis it observed that BART and PEGASUS show ROUGE-I score of 0.308 and 0.245, and METEOR score 0.28 and 0.25 respectively. The outcomes of this study show that the T5 excelled in the ROUGE-1 and METEOR scores which were 0.354 and 0.35 respectively. outcomes of this research offer significant implications for both researchers and practitioners, equipping them with advanced summarization techniques for extracting information effectively from business-related content. In an age where information overload is prevalent, the findings from this study can guide the selection and deployment of text summarization models to enhance information extraction processes, ultimately facilitating more efficient decision-making and information dissemination in the business domain. [ABSTRACT FROM AUTHOR]

Rescue efforts might be significantly complicated in flooded areas. In this study, we examine and evaluate the state-of-the-art in object detection and image enhancement techniques in flooded situations for the purpose of human rescue operations using various image processing, object detection, and low light image enhancement approaches. Partial visible images are difficult due to poor light, low contrast, and scattering. Faster R-CNN, YOLO (You Only Look Once), and SSD (Single Shot Detector) are just a few of the popular object identification methods. Advanced deep learning-based low-light enhancement approaches increase image quality by amplifying faint features, decreasing noise, and correcting color imbalances. These models use auto encoders, generative adversarial networks, and attention processes to rebuild images better than classic enhancement methods, making them useful for rescue pre-processing. The findings emphasized the role of real-time data analysis and communication systems in improving response times and operational efficiency. The application of Generative Adversarial Networks significantly improved the clarity and color accuracy of underwater images. These methods address water's refractive characteristics, floating debris, and human occlusion. For efficient and complete disaster management throughout all phases, subsequent attempts should focus on blending disaster management expertise, image processing techniques, and machine learning tools, as outlined by our study. This research can improve flood monitoring systems and disaster preparedness, response, and recovery. [ABSTRACT FROM AUTHOR]

The financial sector has greatly impacted the monetary well-being of consumers, traders, and financial institutions. In the current era, artificial intelligence is redefining the limits of the financial markets based on state-of-the-art machine learning and deep learning algorithms. There is extensive use of these techniques in financial instrument price prediction, market trend analysis, establishing investment opportunities, portfolio optimization, etc. Investors and traders are using machine learning and deep learning models for forecasting financial instrument movements. With the widespread adoption of AI in finance, it is imperative to summarize the recent machine learning and deep learning models, which motivated us to present this comprehensive review of the practical applications of machine learning in the financial industry. This article examines algorithms such as supervised and unsupervised machine learning algorithms, ensemble algorithms, time series analysis algorithms, and deep learning algorithms for stock price prediction and solving classification problems. The contributions of this review article are as follows: (a) it provides a description of machine learning and deep learning models used in the financial sector; (b) it provides a generic framework for stock price prediction and classification; and (c) it implements an ensemble model—"Random Forest + XG-Boost + LSTM"—for forecasting TAINIWALCHM and AGROPHOS stock prices and performs a comparative analysis with popular machine learning and deep learning models. [ABSTRACT FROM AUTHOR]

Following the COVID-19 pandemic, the healthcare sector has emerged as a resilient and profitable domain amidst market fluctuations. Consequently, investing in healthcare securities, particularly through mutual funds, has gained traction. Existing research on predicting future prices of healthcare securities has been predominantly reliant on historical trading data, limiting predictive accuracy and scope. This study aims to overcome these constraints by integrating a diverse set of twelve external factors spanning economic, industrial, and company-specific domains to enhance predictive models. Employing Long Short-Term Memory (LSTM) and Multiple Linear Regression (MLR) techniques, the study evaluates the effectiveness of this multifaceted approach. Results indicate that incorporating various influencing factors beyond historical data significantly improves price prediction accuracy. Moreover, the utilization of LSTM alongside this comprehensive dataset yields comparable predictive outcomes to those obtained solely from historical data. Thus, this study highlights the potential of leveraging diverse external factors for more robust forecasting of mutual fund prices within the healthcare sector. [ABSTRACT FROM AUTHOR]