Cloud-based Environment Research Articles

Audiovisual translation, translators, and technology: From automation pipe dream to human–machine convergence

Audiovisual translation (AVT), broadly understood as a synonym for media content localization, and not only as a particular practice of linguistic transfer, is undergoing a revolution that was unthinkable only a few years ago – even in those territories where viewers are less accustomed to localized content. Digitalization and technological changes, which have had such an impact on the way audiovisual texts – whether original, localized, or adapted – are produced, distributed, edited, consumed, and shared have also had a substantial impact on the AVT profession. This article explores the ways in which technology has been evolving as an aid to translators: from being merely a clerical aid for transcribing digital texts to automating tasks and integrating machine translation into human translation processes. This it does by providing a range of tools to assist translators in their work processes, progressively migrating both tools and processes to cloud-based environments. The focus is then on AVT, and more particularly on dubbing, where digitalization has shaped the consumer market and posed several challenges to language technology developments and AVT professional practices. Academia has also paid attention to such developments and has increasingly dealt with a number of matters affecting both practice and training to cater to the needs of current media markets. A final word is devoted to proposing a literacy-based framework for the training of translators that embraces technology so as to incorporate automation as an additional aid and which redefines the audiovisual translator’s workstation.

¡Sub! localisation workflows (th)at work

Abstract Over the last few years, cloud-based environments have simplified traditional localisation workflows and have made it possible for virtual teams of audiovisual translation (AVT) professionals to work together from all corners of the earth (Díaz Cintas and Massidda 2019). In addition, AI-powered technologies have been integrated into localisation workflows to accelerate translation processes: this has led to a progressive automation of AVT practices and has created brand new roles for language professionals. This paper presents the preliminary results of the international pilot project ¡Sub! Localisation Workflows (th)at Work (2020–2022). A series of experiments was conducted in the spring of 2021 to compare three different workflows in the subtitling of documentaries: traditional (i.e., using only subtitling software), semi-automated (using automatic speech recognition and captioning) and fully automated (relying on automatic speech recognition, captioning and machine translation). The experiments involved twenty-four final-year MA students and recent graduates from UNINT and Roehampton University (twelve of them working from English into Italian and twelve from Spanish into Italian), in subtitling teams that included a project manager, a spotter, a subtitler, and a reviser. All the work was recorded via screencast technology and documented in a project logbook, a quality assessment form, and a workflow summary sheet. The aim of the experiments was to identify the most effective workflow equation, i.e., the one able to deliver the best quality output in the tightest turnaround time. This paper illustrates the experimental set-up and materials and discusses the preliminary results emerging from a quantitative and qualitative analysis of our data.

Employing the Powered Hybridized Darts Game with BWO Optimization for Effective Job Scheduling and Distributing Load in the Cloud-Based Environment

One of the most frequent issues in cloud computing systems is job scheduling, which is designed to efficiently reduce installation time and cost while concurrently enhancing resource utilisation. Limitations such as accessible implementation costs, high resource utilisation, insufficient make-span, and fast scheduling response lead to the Nondeterministic Polynomial (NP)-hard optimisation problem. As the number of combinations along with processing power increases, job allocation becomes NP-hard. This study employs a hybrid heuristic optimisation technique that incorporates load balancing to achieve optimal job scheduling and boost service provider performance within the cloud architecture. As a result, there are many less problems with the scheduling process. The suggested work scheduling approach successfully resolves the load balancing issue. The suggested Hybridised Darts Game-Based Beluga Whale Optimisation Algorithm (HDG-BWOA) assists in assigning jobs to the machines according to workload. When assigning jobs to virtual machines, factors such as reduced energy usage, minimised mean reaction time, enhanced job assurance ratio, and higher Cloud Data Centre (CDC) resource consumption are taken into account. By ensuring flexibility among virtual computers, this job scheduling strategy keeps them from overloading or underloading. Additionally, by employing this method, more activities are effectively finished before the deadline. The effectiveness of the proposed configuration is guaranteed using traditional heuristic-based job scheduling techniques in compliance with multiple assessment metrics.

BloodSpot 3.0: a database of gene and protein expression data in normal and malignant haematopoiesis.

BloodSpot is a specialised database integrating gene expression data from acute myeloid leukaemia (AML) patients related to blood cell development and maturation. The database and interface has helped numerous researchers and clinicians to quickly get an overview of gene expression patterns in healthy and malignant haematopoiesis. Here, we present an update to our framework that includes protein expression data of sorted single cells. With this update we also introduce datasets broadly spanning age groups, which many users haverequested, with particular interest for researchers studying paediatric leukaemias. The backend of the database has been rewritten and migrated to a cloud-based environment to accommodate the growth, and provide a better user-experience for our many international users. Users can now enjoy faster transfer speeds and a more responsive interface. In conclusion, the continuing popularity of the database and emergence of new data modalities has prompted us to rewrite and futureproof the back-end, including paediatric centric views, as well as single cell protein data, allowing us to keep the database updated and relevant for the years to come. The database is freelyavailable at www.bloodspot.eu.

Point cloud-based environment reconstruction and ray tracing simulations for railway tunnel channels

Radio propagation environment plays a critical role in the performance of wireless communication systems, and understanding channel characteristics is vital for ensuring reliable communication links and optimizing system performance. Ray tracing is an effective method to investigate propagation characteristics in a complex environment, and how to quickly and accurately obtain environmental information needs to be solved. This paper presents dynamic environment reconstruction and ray tracing simulation in railway tunnel environment based on Simultaneous Localization and Mapping (SLAM) algorithm and Poisson reconstruction algorithm. Accurate channel parameters are obtained and analyzed based on ray tracing simulation. Both straight and curved tunnels are considered and investigated, and the results show the channel characteristics in complex railway tunnel environments.

Pothole Detection in Roads using Pretrained Model and Cloud Computing

Abstract—The fundamental objective of this project is to make use of the advanced capabilities offered by technology that is cur- rently available on the market in order to locate and accurately identify potholes. The research identifies potholes in real-time video feeds obtained from vehicles by employing YOLOv8, a dependable pre-trained model for object detection. Utilising an Internet of Things (IoT) gateway, which creates a connection with Kinesis Video Streams in order to collect the video data, makes the procedure simpler and more efficient.The combination of the YOLOv8 algorithm with the Amazon SageMaker platform enables the accurate detection and localization of potholes within the frames of a particular film. The project makes use of the computing power made available by Amazon Web Services (AWS) in order to make the effective processing and analysis of video data inside a cloud-based environment possible.After the algorithm has determined that potholes are present, it will proceed to take precise notes of the coordinates that correlate to each individual hole. The data described above is gathered and saved within the environment provided by AWS, which provides helpful insightsfor operations relating to maintenance and repair. Because of the combination of pretrained models, cloud-based infrastructure, and Internet of Things (IoT) components, a dependable and scalable solution for the prompt identification of potholes has been produced. This has resulted in an improvement in both the safety of road networks and their maintenance. Index Terms—pothole detection, deep learning, cloud comput- ing, object detection, pretrained models, convolutional neural networks

A Novel Cryptographic Technique for Cloud Environment Based on Feedback DNA

Abstract: In the era of cloud computing, ensuring data security is crucial for users and organizations. This paper presents an innovative approach called F-DNAES, which combines DNA cryptography and the Advanced Encryption Standard (AES) algorithm, to enhance data security in cloud-based environments. The proposed methodology focuses on securing data during its transmission and storage in the cloud. By leveraging the unique properties of DNA, such as its storage capacity and stability, along with the robustness of AES encryption, F-DNAES provides a highly secure and efficient solution. The proposed method also ensures the authentication of the Data owners and the users. The F-DNAES model effectively mitigates potential security threats such as phishing attacks, collision attacks, and password guessing attacks. It also offers superior performance in terms of key generation, encryption, and decryption processes. The proposed approach can be applied to various cloud-based scenarios, including IoT infrastructure, web-based applications, and network security. F-DNAES contributes to strengthening data privacy and security, providing users with a trusted and reliable solution in cloud environments.

Cloud-assisted quantum primitive protocols and applications

Abstract Security and privacy have always been key concerns for individuals in various cloud-assisted services. In order to enhance security, we focus on quantum cryptography in novel cloud-based applications. First, we present two quantum primitive protocols to compute XOR of two private bits and AND of two private bits with the assistance of a quantum cloud, respectively. Then, we generalize two-party protocols to the corresponding multi-party cases. These quantum primitive protocols can ensure information-theoretical security and provide long-term security, which are guaranteed by the principles of quantum mechanics. Furthermore, we present a grouping strategy to improve the communication efficiency of multiparty quantum protocols. In addition, we investigate privacy-preserving applications of these quantum primitive protocols in cloud-based environments, e.g., cloud-based Anonymous Voting and Multiparty Private Set Intersection. Finally, simulated experiments show our proposed quantum protocols are correct and feasible with the present quantum technology.

METB-11. EXPANSION OF THE PEDIATRIC BRAIN TUMOR ATLAS: AN OPEN SCIENCE EFFORT OF CHILDREN’S BRAIN TUMOR NETWORK, KIDS FIRST DATA RESOURCE AND CHILDHOOD CANCER DATA INITIATIVE

Abstract Pediatric central nervous system cancers are the leading disease-related cause of death in children and there is urgent need for curative therapeutic strategies for these tumors. To address the urgency, Children’s Brain Tumor Network (CBTN) has advanced an open science model to accelerate the research discovery for pediatric brain tumors. In first phase of Open Pediatric Brain Tumor Atlas (OpenPBTA) effort CBTN together with Pacific Pediatric Neuro-Oncology Consortium (PNOC) and Gabriella Miller Kids First Data Resource Center (KFDRC) created and characterized over 1000 clinically annotated pediatric brain tumors. The second phase of the OpenPBTA, through resource awards and collaboration across KFDRC, the NCI Childhood Cancer Data Initiative (CCDI), Clinical Proteomic Tumor Analysis Consortium (CPTAC), Center for Cancer Research and partnered institutions and foundations has expanded molecular characterization for an additional 1900 pediatric brain tumor patients and their families. This includes the processing and characterization of >8000 specimens across >50 brain tumor diagnoses. This expansion builds off multimodal data including whole genome, RNA, miRNA and methylation sequencing, proteomics, lipidomics and/or metabolomics. Molecular data is linked to longitudinal clinical data, imaging data, histology images, and pathology reports. The data deposition in the cloud-based environment of the NCI’s CCDI and KFDRC to provide near real-time integration, dissemination, processing, and sharing capability. The approach leverages the DRC platform’s cloud-based computational environment through CAVATICA portal shareable pipelines. Data can be explored via PedcBioPortal, a data visualization/analysis application integrating additional public and deposited datasets. This OpenPBTA expansion released with no embargo provides one of the largest deeply characterized cohorts of samples and associated clinical data for >3000 pediatric brain tumor patients. CBTN’s open-science, rapid-release model aims to accelerate pediatric biomarker and drug discovery research and supports clinical trial development on behalf of changing the outcome for kids with brain tumors.

DA-LSTM: A dynamic drift-adaptive learning framework for interval load forecasting with LSTM networks

Load forecasting is a crucial topic in energy management systems (EMS) due to its vital role in optimizing energy scheduling and enabling more flexible and intelligent power grid systems. As a result, these systems allow power utility companies to respond promptly to demands in the electricity market. Deep learning (DL) models have been commonly employed in load forecasting problems supported by adaptation mechanisms to cope with the changing pattern of consumption by customers, known as concept drift. A drift magnitude threshold should be defined to design change detection methods to identify drifts. While the drift magnitude in load forecasting problems can vary significantly over time, existing literature often assumes a fixed drift magnitude threshold, which should be dynamically adjusted rather than fixed during system evolution. To address this gap, in this paper, we propose a dynamic drift-adaptive Long Short-Term Memory (DA-LSTM) framework that can improve the performance of load forecasting models without requiring a drift threshold setting. We integrate several strategies into the framework based on active and passive adaptation approaches. To evaluate DA-LSTM in real-life settings, we thoroughly analyze the proposed framework and deploy it in a real-world problem through a cloud-based environment. Efficiency is evaluated in terms of the prediction performance of each approach and computational cost. The experiments show performance improvements on multiple evaluation metrics achieved by our framework compared to baseline methods from the literature. Finally, we present a trade-off analysis between prediction performance and computational costs.

Observability & Reliability of Microservices Application using DevOps in a Cloud-based Environment

Observability & Reliability of Microservices Application using DevOps in a Cloud-based Environment

End to End Development and Deployment of Predictive Models Using Azure Synapse Analytics

The end-to-end development and deployment of predictive models using Azure Synapse Analytics represents a comprehensive approach to harnessing advanced analytics for data-driven decision-making. This process integrates various stages of the data science lifecycle within a unified cloud-based environment, leveraging Azure Synapse Analytics' capabilities for data integration, exploration, and model management. Initially, the process involves data ingestion and preparation, where Azure Synapse Analytics facilitates seamless data integration from diverse sources, ensuring that the data is clean, relevant, and ready for analysis. The platform’s robust data processing capabilities enable the transformation of raw data into actionable insights. Next, model development is undertaken using Azure Synapse’s built-in support for various machine learning frameworks and languages, which simplifies the creation and training of predictive models. By utilizing automated machine learning features and scalable compute resources, data scientists can efficiently develop and refine models tailored to specific business needs. Following development, the deployment phase involves operationalizing the predictive models within the Azure Synapse environment. This includes deploying models as web services or integrating them into existing workflows to ensure they deliver real-time predictions and insights. Azure Synapse Analytics supports monitoring and management of these models, allowing for continuous performance evaluation and optimization. Overall, Azure Synapse Analytics provides a holistic platform that streamlines the entire predictive modelling lifecycle, enhancing efficiency and scalability while enabling organizations to leverage predictive analytics for strategic advantage. This end-to-end approach not only accelerates the deployment of machine learning models but also ensures they are seamlessly integrated into the broader data ecosystem.

An Effective Comparative Evaluation in 4G and 5G Generation of Wireless Mobile Network

Most business or government services are implemented in a web or cloud-based environment nowadays. For this purpose, websites, mobile applications, and cloud-based services are established in cyberspace so that services may be accessed at any time, from any location. India is one of the largest smartphone marketplaces and an attractive location for smartphone manufacturing multinational corporations. According to data and statistics from Statista.com, India is one of the leading nations with a substantial mobile user market. In 2017, over 134 million cellphones were sold in India, which is a significant number. According to a separate study, the number of people in India who use smartphones is expected to almost reach 450 million by the year 2022. There is a need to improve the performances of present 4G and upcoming 5G Net-work technologies so that a better level of performances may be obtained in the net-work environment in order to support the massive load of smartphone wireless networks. This book focuses on the presentation of the outcomes of advanced 4G and 5G wireless net-works simulated utilizing the advanced implementation tools of cupcarbon.

Prediction of the Topography of the Corticospinal Tract on T1-Weighted MR Images Using Deep-Learning-Based Segmentation.

Tractography is an invaluable tool in the planning of tumor surgery in the vicinity of functionally eloquent areas of the brain as well as in the research of normal development or of various diseases. The aim of our study was to compare the performance of a deep-learning-based image segmentation for the prediction of the topography of white matter tracts on T1-weighted MR images to the performance of a manual segmentation. T1-weighted MR images of 190 healthy subjects from 6 different datasets were utilized in this study. Using deterministic diffusion tensor imaging, we first reconstructed the corticospinal tract on both sides. After training a segmentation model on 90 subjects of the PIOP2 dataset using the nnU-Net in a cloud-based environment with graphical processing unit (Google Colab), we evaluated its performance using 100 subjects from 6 different datasets. Our algorithm created a segmentation model that predicted the topography of the corticospinal pathway on T1-weighted images in healthy subjects. The average dice score was 0.5479 (0.3513-0.7184) on the validation dataset. Deep-learning-based segmentation could be applicable in the future to predict the location of white matter pathways in T1-weighted scans.

An Optimization-Linked Intelligent Security Algorithm for Smart Healthcare Organizations

IoT-enabled healthcare apps are providing significant value to society by offering cost-effective patient monitoring solutions in IoT-enabled buildings. However, with a large number of users and sensitive personal information readily available in today's fast-paced, internet, and cloud-based environment, the security of these healthcare systems must be a top priority. The idea of safely storing a patient's health data in an electronic format raises issues regarding patient data privacy and security. Furthermore, with traditional classifiers, processing large amounts of data is a difficult challenge. Several computational intelligence approaches are useful for effectively categorizing massive quantities of data for this goal. For many of these reasons, a novel healthcare monitoring system that tracks disease processes and forecasts diseases based on the available data obtained from patients in distant communities is proposed in this study. The proposed framework consists of three major stages, namely data collection, secured storage, and disease detection. The data are collected using IoT sensor devices. After that, the homomorphic encryption (HE) model is used for secured data storage. Finally, the disease detection framework is designed with the help of Centered Convolutional Restricted Boltzmann Machines-based whale optimization (CCRBM-WO) algorithm. The experiment is conducted on a Python-based cloud tool. The proposed system outperforms current e-healthcare solutions, according to the findings of the experiments. The accuracy, precision, F1-measure, and recall of our suggested technique are 96.87%, 97.45%, 97.78%, and 98.57%, respectively, according to the proposed method.

JUNO Project: Deployment and Validation of a Low-Cost Cloud-Based Robotic Platform for Reliable Smart Navigation and Natural Interaction with Humans in an Elderly Institution

This paper describes the main results of the JUNO project, a proof of concept developed in the Region of Murcia in Spain, where a smart assistant robot with capabilities for smart navigation and natural human interaction has been developed and deployed, and it is being validated in an elderly institution with real elderly users. The robot is focused on helping people carry out cognitive stimulation exercises and other entertainment activities since it can detect and recognize people, safely navigate through the residence, and acquire information about attention while users are doing the mentioned exercises. All the information could be shared through the Cloud, if needed, and health professionals, caregivers and relatives could access such information by considering the highest standards of privacy required in these environments. Several tests have been performed to validate the system, which combines classic techniques and new Deep Learning-based methods to carry out the requested tasks, including semantic navigation, face detection and recognition, speech to text and text to speech translation, and natural language processing, working both in a local and Cloud-based environment, obtaining an economically affordable system. The paper also discusses the limitations of the platform and proposes several solutions to the detected drawbacks in this kind of complex environment, where the fragility of users should be also considered.

Integrating digital solutions into national health data systems through public-private collaboration: An early experience of the SPICE platform in Kenya.

Public-private collaborative efforts to address healthcare challenges in low- and middle-income countries have been the focus of digital initiatives to improve both access and quality of health services. We report the early feasibility, experience, and learnings of migrating healthcare data generated from a proprietary, privately owned cloud-based environment into an on-premises National Health Data Center (NHDC) in compliance with Kenya's data management legislation. In 2018, Medtronic LABS entered into a partnership with the Kenya Ministry of Health and other stakeholders to improve access to quality services and data availability for non-communicable diseases (diabetes and hypertension), anchored on the SPICE digital health platform. Data migration from SPICE to the NHDC necessitated the establishment of multi-stakeholder coordination structures, alignment on system configuration requirements, provisioning of on-premises servers, data replication and monitoring. The data replication process showed consistency in format and content with no evidence of data loss. The monitoring of the server uptime and availability, however, exposed overall downtime of 15% of the total time tracked between April and December 2022 caused by Internet Protocol address configuration issues, power outages, firewall rule changes, and unscheduled system maintenance. Monthly tracked downtime however reduced from a high of 28% in April 2022 to 5% in December 2022. Our early experience shows that data migration from proprietary host environments to public "one-stop-shop" national data warehouses are feasible provided investments are made in the requisite infrastructure, software and human resource capacity to ensure long-term sustainability, maintenance, and scale to match cloud-based data hosting. Further, digital health solutions developed in collaboration with non-state actors can be integrated into national data systems, saving Governments the cost and efforts of building similar tools while leveraging private sector capacity.

DIGITALIZATION OF TEACHER TRAINING IN UKRAINE IN THE CONTEXT OF THE EXPERIENCE OF HUNGARY AND THE REPUBLIC OF POLAND

The article reveals some recommendations for the digitalization of teacher training in Ukraine based on the experience of Hungary and the Republic of Poland. To solve the tasks set and achieve the purpose of the article, the method of theoretical analysis was used to highlight the peculiarities of the development of the system of digitalization of education in Ukraine; empirical methods were used to study the works of domestic and foreign scholars on the digitalization of teacher training; and generalization was used to present recommendations for improving the digitalization of teacher training in Ukraine, based on the experience of the Republic of Poland and Hungary. It has been determined that the digitalization of education in Ukraine is proceeding at an active pace. The content of the educational levels of the program «Google Digital Tools for Education» is considered. It is found that a significant indicator of achieving digitalization of the national education system is the introduction and active development of the Unified State Electronic Database on Education, whose main purpose is to provide individuals and legal entities with information in the field of education. It has been established that the Unified State Electronic Database on Education has been modernized to ensure the possibility of admission to higher education institutions in times of war. Furthermore, it has been found that in the context of developing recommendations for Ukraine on the digitalization of teacher training, taking into account the experience of Hungary and Poland, it is advisable to focus on the need for intensive development of the following technologies: artificial intelligence; augmented and virtual reality; robotization; the Internet of Things; media education; blockchain; cloud-based environments; gamification; interdisciplinary, etc. It has been determined that digital competence is an important component of the professionalism of a modern teacher or lecturer, and at the same time, indicators of its effective formation ensure the success of human functioning in modern society. The positive aspects of the gamification environment are highlighted. Useful online services for teachers are presented. Recommendations for the digitalization of teacher training in Ukraine are proposed, taking into account the experience of Hungary and the Republic of Poland.

IoMT Meets Machine Learning: From Edge to Cloud Chronic Diseases Diagnosis System.

In conventional healthcare, real-time monitoring of patient records and information mining for timely diagnosis of chronic diseases under certain health conditions is a crucial process. Chronic diseases, if not diagnosed in time, may result in patients' death. In modern medical and healthcare systems, Internet of Things (IoT) driven ecosystems use autonomous sensors to sense and track patients' medical conditions and suggest appropriate actions. In this paper, a novel IoT and machine learning (ML)-based hybrid approach is proposed that considers multiple perspectives for early detection and monitoring of 6 different chronic diseases such as COVID-19, pneumonia, diabetes, heart disease, brain tumor, and Alzheimer's. The results from multiple ML models are compared for accuracy, precision, recall, F1 score, and area under the curve (AUC) as a performance measure. The proposed approach is validated in the cloud-based environment using benchmark and real-world datasets. The statistical analyses on the datasets using ANOVA tests show that the accuracy results of different classifiers are significantly different. This will help the healthcare sector and doctors in the early diagnosis of chronic diseases.

A Cloud-Based Deep Learning Framework for Early Detection of Pushing at Crowded Event Entrances

Crowding at the entrances of large events may lead to critical and life-threatening situations, particularly when people start pushing each other to reach the event faster. Automatic and timely identification of pushing behavior would help organizers and security forces to intervene early and mitigate dangerous situations. In this paper, we propose a cloud-based deep learning framework for automatic early detection of pushing in crowded event entrances. The proposed framework initially modifies and trains the EfficientNetV2B0 Convolutional Neural Network model. Subsequently, it integrates the adapted model with an accurate and fast pre-trained deep optical flow model with the color wheel method to analyze video streams and identify pushing patches in real-time. Moreover, the framework uses live capturing technology and a cloud-based environment to collect video streams of crowds in real-time and provide early-stage results. A novel dataset is generated based on five real-world experiments and their associated ground truth data to train the adapted EfficientNetV2B0 model. The experimental setups simulated a crowded event entrance, while the ground truths for each video experiment was generated manually by social psychologists. Several experiments on the videos and the generated dataset are carried out to evaluate the accuracy and annotation delay time of the proposed framework. The experimental results show that the proposed framework identified pushing behaviors with an accuracy rate of 87% within a reasonable delay time.