Browse Items (11810 total)
Sort by:
-
Clinical Intelligence: Deep Reinforcement Learning for Healthcare and Biomedical Advancements
Deep reinforcement learning (DRL) is showing a remarkable impact in the healthcare and biomedical domains, leveraging its ability to learn complex decision-making policies from raw data through trial-and-error interactions. DRL can effectively extract the characteristic information in the environment, propose effective behavior strategies, and correct errors that occurred during the training process. Targeted toward healthcare professionals, researchers, and technology enthusiasts, this chapter begins with notable applications of DRL in healthcare, including personalized treatment recommendations, clinical trial optimization, disease diagnosis, robotic surgery and assistance, mental health support systems, chronic disease management and scheduling, and a few more. It also delves on challenges such as data privacy, interpretability, regulatory compliance, validation, and the need for domain expertise to ensure safe and effective deployment. Next, the chapter seamlessly transitions into DRL algorithms contributing to the biomedical field which are gaining traction due to their potential to provide timely and personalized interventions. Over time, the research community has proposed several methods and algorithms within the field of deep reinforcement learning that help agents learn optimal policies from rich data. Healthcare data is often complex, high-dimensional, and unstructured, such as medical images, genomics data, and patient records. The healthcare-suitable DRL algorithms such as Q-learning, SARSA, Bayesian, actor-critic, reinforcement learning (RL), Deep-Q-Networks (DQN), and Monte Carlo Tree Search (MCTS) are highlighted. In addition, the section offers guidelines for the application of DRL to healthcare and biomedical problems, aiming at providing indications to the designer of new applications in order to choose among different RL methods. Furthermore, a case study is included to fully realize the revolutionary benefits of DRL in healthcare environments, aiming to bridge the gap between theory and practice. The case study presents a remarkable impact on categories such as precision medicine, dynamic treatment regime, medical imaging, diagnostic systems, control systems, chat-bots and advanced interfaces, and healthcare management systems. 2024 Scrivener Publishing LLC. -
Formula One Race Analysis Using Machine Learning
Formula One (also known as Formula 1 or F1) is the highest class of international auto-racing for single-seater formula racing cars sanctioned by the Fation International de automobile (FIA). The World Drivers Championship, which became the FIA Formula One World Championship in 1981, has been one of the premier forms of racing around the world since its inaugural season in 1950. This article looks at cost-effective alternatives for Formula 1 racing teams interested in data prediction software. In Formula 1 racing, research was undertaken on the current state of data gathering, data analysis or prediction, and data interpretation. It was discovered that a big portion of the leagues racing firms require a cheap, effective, and automated data interpretation solution. As the need for faster and more powerful software grows in Formula 1, so does the need for faster and more powerful software. Racing teams benefit from brand exposure, and the more they win, the more publicity they get. The papers purpose is to address the problem of data prediction. It starts with an overview of Formula 1s current situation and the billion-dollar industrys history. Racing organizations that want to save money might consider using Python into their data prediction to improve their chances of winning and climbing in the rankings. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
From maximum force to the field equations of general relativity and implications
There are at least two ways to deduce Einstein's field equations from the principle of maximum force c4/4G or from the equivalent principle of maximum power c5/4G. Tests in gravitational wave astronomy, cosmology, and numerical gravitation confirm the two principles. Apparent paradoxes about the limits can all be resolved. Several related bounds arise. The limits illuminate the beauty, consistency and simplicity of general relativity from an unusual perspective. 2022 World Scientific Publishing Company. -
Physics of Gravitational Waves: Sources and Detection Methods
[No abstract available] -
Crisis management, destination recovery and sustainability: Tourism at a crossroads
The COVID-19 pandemic brought travel to a halt and the global tourism industry has been one of the sectors hit hardest during the pandemic. This book looks at how the tourism industry can enhance its resilience and prepare for future crises more effectively. The book provides insights into the economic, social, geopolitical and environmental implications of the COVID-19 pandemic on the tourism and hospitality industries and the responses in diverse international contexts. It highlights key concepts and includes cases with real-life applications. The book also discusses future research directions in a post-pandemic scenario. This book will be an invaluable resource for practitioners in the areas of tourism and crisis management and for readers to compare and contrast tourism destination recovery and crisis management practices through different research methodologies and settings. 2023 selection and editorial matter, James Kennell, Priyakrushna Mohanty, Anukrati Sharma and Azizul Hassan. All rights reserved. -
Introduction: Tourism at a crossroads
[No abstract available] -
Facial Recognition Model Using Custom Designed Deep Learning Architecture
Facial Recognition is widely used in some applications such as attendance tracking, phone unlocking, and security systems. An extensive study of methodologies and techniques used in face recognition systems has already been suggested, but it doesn't remain easy in the real-world domain. Preprocessing steps are mentioned in this, including data collection, normalization, and feature extraction. Different classification algorithms such as Support Vector Machines (SVM), Nae Bayes, and Convolutional Neural Networks (CNN) are examined deeply, along with their implementation in different research studies. Moreover, encryption schemes and custom-designed deep learning architecture, particularly designed for face recognition, are also covered. A methodology involving training data preprocessing, dimensionality reduction using Principal Component Analysis, and training multiple classifiers is further proposed in this paper. It has been analyzed that a recognition accuracy of 91% is achieved after thorough experimentation. The performance of the trained models on the test dataset is evaluated using metrics such as accuracy and confusion matrix. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Interacting Dark Energy and Its Implications for Unified Dark Sector
Alternative dark energy models were proposed to address the limitation of the standard concordance model. Though different phenomenological considerations of such models are widely studied, scenarios where they interact with each other remain unexplored. In this context, we study interacting dark energy scenarios (IDEs), incorporating alternative dark energy models. The three models that are considered in this study are time-varying ?, Generalized Chaplygin Gas (GCG), and K-essence. Each model includes an interaction rate ? to quantify energy density transfer between dark energy and matter. Among them, GCG coupled with an interaction term shows promising agreement with the observed TT power spectrum, particularly for ?<70, when ? falls within a specific range. The K-essence model (??0.1) is more sensitive to ? due to its non-canonical kinetic term, while GCG (??1.02) and the time-varying ? (??0.01) models are less sensitive, as they involve different parameterizations. We then derive a general condition when the non-canonical scalar field ? (with a kinetic term Xn) interacts with GCG. This has not been investigated in general form before. We find that current observational constraints on IDEs suggest a unified scalar field with a balanced regime, where it mimics quintessence behavior at n<1 and phantom behavior at n>1. We outline a strong need to consider alternative explanations and fewer parameter dependencies while addressing potential interactions in the dark sector. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. -
Parametric effect on machining characteristics of laser machined Al7075TiB2 in-situ composite
The effect of laser parameters on the machining characteristics of an Al7075 based in-situ metal matrix composite reinforced with Titanium diboride(TiB2) is investigated. The cutting speed (at 10001200 m/hr), stand-off distance (SOD) (0.30.5 mm), and gas pressure (0.50.7 bar) were studied. Scanning electron microscopy (SEM) was used to validate the machining behaviour of in-situ composites. Surface roughness and dimensional error decrease as the SOD increases up to 0.4 mm, but both increases as the SOD increases to 0.5 mm. whereas the volumetric material removal rate (VMRR) increases up to 0.4 mm SOD and then decreases as SOD increases (0.5 mm). Surface roughness, VMRR, and dimensional error were all found to increase with laser speed. Surface roughness and dimensional error increase as gas pressure increase up to 0.5 bar, then decreases. The VMRR, on the other hand, increased continuously as the assist gas pressure increased. Copyright 2021 Inderscience Enterprises Ltd. -
Experimental investigation of tribocorrosion
This chapter discusses various techniques available for evaluation of tribocorrosion behavior of industrial components, their applications, and limitations. Numerous influential factors of tribocorrosion, their mechanisms, and their characteristics have been discussed at length. Further, a case study of tribocorrosion behavior of aluminum-based in situ metal matrix composites have been deliberated comprehensively. 2021 Elsevier Inc. All rights reserved. -
Friction and wear behaviour of copper reinforced acrylonitrile butadiene styrene based polymer composite developed by fused deposition modelling process
This paper focuses on the development of copper filled Acrylonitrile Butadiene Styrene (ABS) composites by fused deposition modelling (FDM) and to characterize its friction and wear behaviour. Twin screw extrusion technique was employed to extract copper-ABS composite filament. Three different materials were tested, i.e. pure ABS, ABS+2.5wt% Cu and ABS+5wt% Cu. Friction and wear characteristics of pure ABS and copper filled ABS composites were tested under various loads and sliding velocities. Addition of Copper powder has significantly improved the friction and wear properties of the developed composites. Further, it is also observed that friction and wear behaviour increased with increase in copper content in ABS. Worn out surfaces were subjected to scanning electron microscopy studies to analyse and identify the possible wear mechanisms involved. Faculty of Mechanical Engineering, Belgrade. -
Bioinformatics Research Challenges and Opportunities in Machine Learning
This research work has studied about the utilization of machine learning algorithms in bioinformatics. The primary purpose of studying this is to understand bioinformatics and different machine algorithms which are used to analyze the biological data present with us. This research study discusses about different machine learning approaches like supervised, unsupervised, and reinforcement which play an essential role in understanding and analyzing biological data. Machine learning is helping us to solve a wide range of bioinformatics problems by describing a wide range of genomics sequences and analyzing vast amounts of genomic data. One of the biggest real-world problems is that machine learning is helping us to identify cancer with a given gene expression, which is done using a support vector machine. In addition, this study discusses about the classification of molecular data, which will help find out minor diseases. With the advancement of machine learning in healthcare and other related applications, data collection becomes a tedious process. This article also focuses on some of the research problems in machine learning domain. The uses of machine learning algorithms in bioinformatics have been extensively studied. These objectives will help to understand bioinformatics and different machine algorithms that are used to analyze the biological data. This research study presents different machine learning approaches like supervised, unsupervised, and reinforcement, which play an important role in understanding and analyzing biological data. Machine learning helps to solve a wide range of bioinformatics related challenges by describing a wide range of genomics sequences and analyzing huge amounts of genomic data. One of the biggest real-time challenges is that the machine learning is helping to identify cancer with a given gene expression, and this is done by using a support vector machine. Finally, this research study has discussed about the classification of molecular data, which will be helpful in finding out minor diseases. 2022 IEEE. -
A Comparative Performance Analysis of Convolution W/O OpenCL on a Standalone System
Initial approach of this paper is to provide a deep understanding of OpenCL architecture. Secondly, it proposes an implementation of a matrix and image convolution implemented in C (Serial Programming) and OpenCL (Parallel Programming), to describe detailed OpenCL programming flow and to provide a comparative performance analysis. The implementation is being carried on AMD A10 APU and various algebraic scenarios are created, to observe the performance improvement achieved on a single system when using Parallel Programming. In the related works authors have worked on AMDAPPSDK samples such as N-body & SimpleGL to understand the concept of vector data types in OpenCL and OpenCL-GL interoperability, have also implemented 3-D particle bouncing concept in OpenCL & 3D-Mesh rendering using OpenCL. Lastly, authors have also illuminated about their future work, where they intend to implement a novel algorithm for mesh segmentation using OpenCL, for which they have tried to form a strong knowledge base through this work. 2015 IEEE. -
Videoconferencing-delivered psychological intervention for the treatment of COVID-19 related psychological distress in University students: study protocol for a randomised controlled trial in India
Background: The mental health impacts of the COVID-19 pandemic have been profound. This paper outlines the study protocol for a trial that tests the efficacy of a brief group-based psychological intervention (Coping with COVID; CWC), relative to Supportive Counselling, to reduce distress associated with COVID-19 in a young adult population in Bangalore, India. Methods: A single-blind, parallel, randomized controlled trial will be carried out via video conferencing in a small group format. Following informed consent, adults that screen positive for levels of psychological distress (Kessler 10 (K-10 score ? 20) and have access to a videoconferencing platform will be randomised to an adapted version of CWC (n = 90) or Supportive Counselling (SC) (n = 90). The primary outcome will be reduction in psychological distress including anxiety and depression at 2-months post treatment. Secondary outcomes include worry, positive wellbeing, and stress in relation to COVID-19. Discussion: This treatment trial will assess whether CWC will result in reduced distress relative to Supportive Counselling in a young adult population in Bangalore, India. This study will yield important insights into the role of nonspecific factors versus the interventions components in impacting COVID-19 related distress. Trial registration: This trial was prospectively registered on the Australian New Zealand Clinical Trials Registry (ACTRN12621001064897). Ethics and dissemination: Ethics approval has been obtained from the participating institution, CHRIST University in Bangalore. Results of the trial will be submittedfor publication in peer reviewed journals and findings presented at scientific conferences and to key service providers and policy makers. 2022, The Author(s). -
Narrating Trauma as Victims of Human Trafficking in China: A Study on Select North Korean Memoirs
The memoirs titled In Order to Live; A North Korean Girl's Journey, to Freedom and; A Thousand Miles to Freedom: My Escape from North Korea are written by Yeonmi Park and Eunsun Kim two women who managed to escape from North Korea. They went through an experience of being forced into labour in China as victims of trafficking. In their memoirs these authors vividly depict the pain that comes with being exploited. The main aim of this study is to analyse how memoirs can effectively address the issue of trafficking. These remarkable women skilfully use the memoir genre to make a personal plea for action. They strategically make choices appeal to readers emotions openly share their distressing experiences and support their stories with research and evidence that connect their experiences with the broader problem of human trafficking in China. This study clearly shows that both these memoirs emphasize the importance of the memoir genre in advocating for rights. It also highlights how survivor memoirs have the potential to inspire advocacy and involvement, in combating trafficking. 2025 Sciedu Press. All rights reserved. -
Inpatient complaining behaviour: A study on the overt and covert behaviour of inpatients in Indian hospitals
Consumer dissatisfaction and complaining behaviour have always been a topic of discussion in educational institutes and industries alike. Whereas dissatisfaction with product purchases and subsequent returns or associated consumer responses is very common, the same in the service sector has been quite different. In India, it is not only the patient who decides, which healthcare service to opt for, because Indians are culturally embedded in a system of collective consumption where other family members or relatives or friends also influence their decision-making. This paper is an exploratory study done to comprehend the chosen behavioural responses of dissatisfied inpatients in India through a questionnaire survey. The survey followed a retrospective recall technique in which the recall window was fixed at six months. The sampling technique followed was probability sampling. The data collection tool was structured and self-administered questionnaire administered in the sampled nine districts of Kerala. A good number of respondents attributed their overt complaining behaviour to lack of cordiality of doctors, nurses or the attending staff and lack of proper care and concern from doctors or nurses. Post complaining, service recovery was found to be satisfactory for most of the complainers. 2020, Kamala-Raj Enterprises. All rights reserved. -
Blowing Your Own Trumpet: How to Increase the Online Visibility of Your Publication?
After seeing ones manuscript in the print form in a journal, the author feels a sense of elation which is indescribable. However, if one really want peers and other researchers to take note of the work, some more effort is needed. With the massive increase in the number of biomedical journals in print supplemented by another large chunk onlinequite a few published papers remain unread by majority of the readers. The availability of social sites, persistent identifiers, and manuscript-sharing sites has simplified the job of increasing the impact of an article. We herein share some of these tricks-of-the-trade. 2018, Indian Academy of Pediatrics. -
An internet of health things-driven deep learning framework for detection and classification of skin cancer using transfer learning
As specified by World Health Organization, the occurrence of skin cancer has been growing over the past decades. At present, 2 to 3 million nonmelanoma skin cancers and 132 000 melanoma skin cancers arise worldwide annually. The detection and classification of skin cancer in early stage of development allow patients to have proper diagnosis and treatment. The goal of this article is to present a novel deep learning internet of health and things (IoHT) driven framework for skin lesion classification in skin images using the concept of transfer learning. In proposed framework, automatic features are extracted from images using different pretrained architectures like VGG19, Inception V3, ResNet50, and SqueezeNet, which are fed into fully connected layer of convolutional neural network for classification of skin benign and malignant cells using dense and max pooling operation. In addition, the proposed system is fully integrated with an IoHT framework and can be used remotely to assist medical specialists in the diagnosis and treatment of skin cancer. It has been observed that performance metric evaluation of proposed framework outperformed other pretrained architectures in term of precision, recall, and accuracy in detection and classification of skin cancer from skin lesion images. 2020 John Wiley & Sons, Ltd. -
Predictive analytics in cryptocurrency using neural networks: A comparative study
This paper is concerned with assessing different neural network based predictive models. Each of these predictive models has one goal and that is to predict the price of a cryptocurrency, Bitcoin is the cryptocurrency taken into consideration. The models will be focusing on predicting the USD equivalent value of bitcoin using historical data and live data. The neural network models being assessed are a Convolutional Neural Network, and two variations of the Recurrent Neural Network that are Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). The goal is to observe the validation loss of each model and also the time it takes to train or epoch for each training set which basically just determine its efficiency and performance. The results that are achieved are almost what was expected as LSTM outperforms CNN but the when we take a look at GRU, it is at par with LSTM. However, CNN is quicker at training or creating epochs and the validation loss is acceptable and not too high but it looks so when it is compared with the Recurrent Neural Networks such as Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). BEIESP. -
Integrating deep learning in an IoT model to build smart applications for sustainable cities
These days, many CS experts focus their efforts on IoT. IoT is an emerging & cutting-edge technology that enables many items, including vehicles and home appliances, to connect and cooperate via mechanisms like machine to machine communication, big data, and AI. It has found use in a wide range of settings, from smart homes and cities, to healthcare and agriculture, to factory automation. Smart cities are becoming smarter, cars are getting more features, and health and fitness devices are getting more sophisticated thanks to the internet of things. Many problems that are directly relevant to the IoT's development have yet to be resolved. The exponential development of IoT has given birth to new problems, including concerns about personal data and security. There is need of a comprehensive approach that tackles the scalability, security, efficiency, and privacy concerns raised by the widespread deployment of IoT. 2023, IGI Global.