Software Resources Research Articles

PARALLEL AND DISTRIBUTED COMPUTING TECHNOLOGIES FOR AUTONOMOUS VEHICLE NAVIGATION

Context. Autonomous vehicles are becoming increasingly popular, and one of the important modern challenges in their development is ensuring their effective navigation in space and movement within designated lanes. This paper examines a method of spatial orientation for vehicles using computer vision and artificial neural networks. The research focused on the navigation system of an autonomous vehicle, which incorporates the use of modern distributed and parallel computing technologies.
 Objective. The aim of this work is to enhance modern autonomous vehicle navigation algorithms through parallel training of artificial neural networks and to determine the optimal combination of technologies and nodes of devices to increase speed and enable real-time decision-making capabilities in spatial navigation for autonomous vehicles.
 Method. The research establishes that the utilization of computer vision and neural networks for road lane segmentation proves to be an effective method for spatial orientation of autonomous vehicles. For multi-core computing systems, the application of parallel programming technology, OpenMP, for neural network training on processors with varying numbers of parallel threads increases the algorithm’s execution speed. However, the use of CUDA technology for neural network training on a graphics processing unit significantly enhances prediction speeds compared to OpenMP. Additionally, the feasibility of employing PyTorch Distributed Data Parallel (DDP) technology for training the neural network across multiple graphics processing units (nodes) simultaneously was explored. This approach further improved prediction execution times compared to using a single graphics processing unit.
 Results. An algorithm for training and prediction of an artificial neural network was developed using two independent nodes, each equipped with separate graphics processing units, and their synchronization for exchanging training results after each epoch, employing PyTorch Distributed Data Parallel (DDP) technology. This approach allows for scalable computations across a higher number of resources, significantly expediting the model training process.
 Conclusions. The conducted experiments have affirmed the effectiveness of the proposed algorithm, warranting the recommendation of this research for further advancement in autonomous vehicles and enhancement of their navigational capabilities. Notably, the research outcomes can find applications in various domains, encompassing automotive manufacturing, logistics, and urban transportation infrastructure. The obtained results are expected to assist future researchers in understanding the most efficient hardware and software resources to employ for implementing AI-based navigation systems in autonomous vehicles. Prospects for future investigations may encompass refining the accuracy of the proposed parallel algorithm without compromising its efficiency metrics. Furthermore, there is potential for experimental exploration of the proposed algorithm in more intricate practical scenarios of diverse nature and dimensions.

Analysis of the perception of auditors from a federal public network HEI concerning the institutionalization of internal control practices

Purpose: To analyse the perception of auditors from a federal public network HEI on the institutionalization of internal control practices.
 Methodology: The questionnaire was administered to internal auditors from a federal public network HEI, and the content of their answers was analysed using Iramuteq® software. The software resources used were factor analysis, similarity analysis and word clouds. These resources served to capture the intended meanings in the set of answers of the three research participants and how their words are associated with the institutionalization of control practices.
 Results: The auditors presented a more critical perception of the institutionalization process in the sedimentation phase of internal control practices, although they reported aspects that confirm actions corresponding to all phases of this process in the focal HEI.
 Contributions of the Study: This study confirms that internal auditors from a public HEI in the federal network better perceive the practices of internal control when they are in the sedimentation phase, which influences their evaluation of these university practices.

СПОСОБ ЗАЩИТЫ КОРПОРАТИВНОЙ СЕТИ НА ОСНОВЕ ДИНАМИЧЕСКОГО РАСПРЕДЕЛЕНИЯ ИНФОРМАЦИОННЫХ РЕСУРСОВ

The general trend in ensuring network security is the transition to the use of comprehensive information security systems. As the statistics of cyber attacks have shown, the objects of destructive influences, as a rule, are software and information resources of corporate networks. Within the framework of the well-known concept of comprehensive protection of network resources, the principle of situational transfer of information resources to protected nodes is substantiated. The article formulates the problem of dynamic distribution of local databases across nodes of a corporate information network. The implementation of such a mechanism is carried out in the event of a threat to the integrity of information resources by a priori formalization and initiation of an algorithm for solving the problem of assignments of a special type in Boolean variables. The features of the mathematical model of an extremal problem are the minimization of the cost of computing resources when solving a set of applied problems and taking into account the requirement for placing local databases on several network nodes with backup capabilities. In other words, a situationally formed plan for storing information resources involves placing one local database on at least the main and backup servers. The article considers the general methodology for determining the plan for placing databases on corporate network nodes and an example of its numerical implementation using the integer programming method. Based on the research results, recommendations are formulated consisting of choosing the optimal option for placing distributed database components on corporate network nodes, which ensures its full functionality and minimizes the risks of violating the integrity of information resources.

Дослідження моделей та алгоритмів систем локалізацій джерел магнітних аномалій

Introduction. The application of modern geophysical methods are caused by the challenges of nowadays Ukraine standing with. The high efficiency of geophysical research is shown by the methods of magnetic exploration. Method of analyzing the array of data from the magnetometer is used to localize the magnetic anomaly’s sources. Such localization is implemented by using various mathematical models and algorithms of software systems. Purpose. The aim of the article is to show an overview of mathematical models and algorithms for the localization of magnetic anomalies’ sources (disturbances). They allow to speed up the processing of magnetometric research’s data and visualize the obtained results. Methods. The article examines the mathematical models of the magnetic anomaly< such as magnetic dipole model, the Gaussian model, the Schwartz model. The multilayer model, and also provides the overview of the main methods for the localization of the described anomaly – the filtering method, the least square method, the gradient analysis method. A list of software and online resources is given, this software is used to analyze magnetometer data and locate magnetic anomalies’ sources. Results. Four mathematical models of magnetic anomalies that allow describing objects of various configurations are considered in the article, and the main methods of determining these objects in the magnetometer data array are given. The article presents the most popular software used for magnetometric data processing. Most of the software is used in geophysics for deep research and requires significant computing resources. A software application was proposed and developed. It allows importing data from the moving platform and magnetometer, analyzing data and visualizing the results. Conclusion. The results of the review emphasize the importance of improving existing mathematical models and developing specialized software for magnetic anomalies’ source localization.

Enhancement of Cloud Computing Environment Using Machine Learning Algorithms MLCE

Cloud computing is an evolving and high-demand research field at the forefront of technological advancements. It aims to provide software resources and operates based on service-oriented delivery. Within the infrastructure as a service (IaaS) framework, the cloud offers end customers access to crucial infrastructure resources, including CPU, bandwidth, and memory. When a cloud system fails to deliver as expected, it is referred to as an event, signifying a deviation from the anticipated service. To meet their service-level agreement (SLA) obligations, cloud service providers (CSPs) must ensure continuous access to fault-tolerant, on-demand resources for their clients, particularly during outages. Consequently, finding the most efficient ways to accomplish tasks while considering the rapid depletion of resources has become an urgent concern. Researchers are actively working to develop optimal strategies tailored to the cloud environment. Machine learning plays a critical role in these endeavors, serving as a key component in various cloud computing platforms. This study presents a comprehensive literature review of current research papers that employ machine learning algorithms to propose strategies for optimizing cloud computing environments. Additionally, the survey provides authors with invaluable resources by extensively exploring a diverse range of machine learning techniques and their applications in the field of cloud computing. By examining these areas, researchers aim to enhance their understanding of efficient resource allocation and scheduling, addressing the challenges posed by resource scarcity while meeting SLA obligations. Index Terms— Cloud computing, Resource allocation Prediction, Energy-efficient resource management, Task Scheduling, Machine Learning.

Compressing the Geospatial Data of Testing Grounds

The paper discusses an algorithm for obtaining the compressed spatial images of testing grounds, which are described by attribute data. The attributive representations of data make it possible to use the hardware and software resources of geographical information systems (GIS) more economically. The objects, that can be presented by a boundary, are considered as the observable ones. The efficiency of the testing ground description is achieved by representing all its areas by boundaries, encoding the boundaries using the Freeman code, and applying the entropy encoding at the last stage of image processing. At the same time, the compressed set of attributive data can be unpacked into the original image with almost no recovery errors or with acceptable accuracy, but not below the limit set by the specification. The theoretical principles of the method are illustrated by the example of processing the segmented image of the contour. The comparative assessment of the efficiency of compression of the combined method under consideration and that of the entropy encoding method is presented.

Інформаційна технологія і програмне забезпечення для імітаційного моделювання, синтезу і досліджень методів криптографічного захисту даних

The described information technology for improving data protection (ITIDP) in information communication systems (ICS) is built on the basis of a system approach for the implementation of hardware and software solutions for encryption/decryption of data flows in a given continuum of hardware-software-space-time limitations. The formulation of the task for the implementation of ITIDP is substantiated, and a variant of its architecture is proposed. Examples of the development of possible hardware and software modules and resources for the creation of both ITIDP and ICS with increased protection of real-time data flows are given. The issues of choosing methods and means of data encryption in real technical systems and criteria for assessing the necessity and adequacy of encrypted protection of information flows depending on the usefulness and confidentiality of transmitted data are discussed. As a practical approbation of the application of the proposed technology for solving applied problems, examples of the synthesis and research of a special processor for a block cipher with sequential data processing and dynamic key correction, as well as the results of research and optimization of the RSA encryption model for its use in critical application mobile systems with limited hardware and software resources. It is shown that for systems with limited hardware resources in the RSA model of the cipher, it is more correct to use not the Euler function, but the Carmichael function. This approach, together with the use of a modified method of successive approximations according to the rules of modular algebra for calculating large powers of a large base with the subsequent determination of the remainder by a given modulus of a very large number, makes it possible to remove restrictions on the bit rate of data in low-power computers and speed up data decryption processes. The use of modular architecture in the proposed information technology ensures its scalability and quick reconfiguration for the study of various methods of cryptographic data protection.

Computer Network Data Management Model Based on Edge Computing

Data reliability and confidence in the data are very important issues, especially when the system integrates fraud or false information. The misusing of data collected may create serious problems. With the fast development of computing techniques, much data are collected from various terminals and industrial devices. Edge computing operates by driving data, software and computer resources from the centralized network to its extremes, allowing pieces of knowledge to lie on distributed cloud networks. Its target customers continue to use commercial Internet application software for every internet customer. Edge computing is used to provide delay-free customer experience assistance for features of the Internet of Things (IoT) services on the edge of the user network. The document identifies an IoT computing platform collaborating with the edge competitive data management latency (CDML) tool. This approach separately categorizes edge layer requests and response data over time using demand-density driven optimization. A difference-based optimization optimizes the frame limits for simultaneous request processing and exact allocation of data. The architectural efficiency of edge computing can be assessed by comparing latency, bandwidth usage, and overhead. Furthermore, estimating the availability, credibility and confidentiality of security solutions within each party would take into consideration security concerns in edge computing and propose a safety assessment process for IoT networks with edge computing. This procedure is finally validated using appropriate tests, and the resulting findings are examined to demonstrate the method’s accuracy. Experimental data are used to validate methods to request maintenance and processing, response time, resource utilization and contract period. In comparison to current approaches, the results of the proposed CDML are measured with a percentage of 97.90%. The proposed system enhances the request and response comparison ratio 97.5%, analyzing request performance ratio 98.1%, response with time analysis ratio of 98.3%, data allocation approach analysis ratio 97.7%.

Equation-based and data-driven modeling: Open-source software current state and future directions

A review of current trends in scientific computing reveals a broad shift to open-source and higher-level programming languages such as Python and growing career opportunities over the next decade. Open-source modeling tools accelerate innovation in equation-based and data-driven applications. Significant resources have been deployed to develop data-driven tools (PyTorch, TensorFlow, Scikit-learn) from tech companies that rely on machine learning services to meet business needs while keeping the foundational tools open. Open-source equation-based tools such as Pyomo, CasADi, Gekko, and JuMP are also gaining momentum according to user community and development pace metrics. Integration of data-driven and principles-based tools is emerging. New compute hardware, productivity software, and training resources have the potential to radically accelerate progress. However, long-term support mechanisms are still necessary to sustain the momentum and maintenance of critical foundational packages.

A toolbox of machine learning software to support microbiome analysis

The human microbiome has become an area of intense research due to its potential impact on human health. However, the analysis and interpretation of this data have proven to be challenging due to its complexity and high dimensionality. Machine learning (ML) algorithms can process vast amounts of data to uncover informative patterns and relationships within the data, even with limited prior knowledge. Therefore, there has been a rapid growth in the development of software specifically designed for the analysis and interpretation of microbiome data using ML techniques. These software incorporate a wide range of ML algorithms for clustering, classification, regression, or feature selection, to identify microbial patterns and relationships within the data and generate predictive models. This rapid development with a constant need for new developments and integration of new features require efforts into compile, catalog and classify these tools to create infrastructures and services with easy, transparent, and trustable standards. Here we review the state-of-the-art for ML tools applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on ML based software and framework resources currently available for the analysis of microbiome data in humans. The aim is to support microbiologists and biomedical scientists to go deeper into specialized resources that integrate ML techniques and facilitate future benchmarking to create standards for the analysis of microbiome data. The software resources are organized based on the type of analysis they were developed for and the ML techniques they implement. A description of each software with examples of usage is provided including comments about pitfalls and lacks in the usage of software based on ML methods in relation to microbiome data that need to be considered by developers and users. This review represents an extensive compilation to date, offering valuable insights and guidance for researchers interested in leveraging ML approaches for microbiome analysis.

Exploring the Components of Management Information Systems: Software, Database, and Brainware - A Literature Review

A more in-depth information system is often referred to as a sub-system, which is a more specific component of a larger system. Information systems have close relationships and interdependencies with other sub-systems, making them inseparable from one another. An information system is just one component of various existing sub-systems, managed as property by a specific institution, organization, or company. Previous research or relevant studies aim to strengthen theories or phenomena related to the influence among variables. This article is structured using a qualitative method sourced from previous research literature by experts. The review's findings reveal components influencing Management Information Systems, namely: Software, Database, and Human Resources (Brainware). The results of this literature review indicate that 1) Software has an impact on Management Information Systems; 2) Databases also influence Management Information Systems; and 3) Human Resources also affect Management Information Systems.

Building expertise on FAIR through evolving Bring Your Own Data (BYOD) workshops: describing the data, software, and management- focused approaches and their evolution

Abstract Since 2014, “Bring Your Own Data” workshops (BYODs) have been organised to inform people about the process and benefits of making resources Findable, Accessible, Interoperable, and Reusable (FAIR, and the FAIRification process). The BYOD workshops’ content and format differ depending on their goal, context, and the background and needs of participants. Data-focused BYODs educate domain experts on how to make their data FAIR to find new answers to research questions. Management-focused BYODs promote the benefits of making data FAIR and instruct project managers and policy-makers on the characteristics of FAIRification projects. Software-focused BYODs gather software developers and experts on FAIR to implement or improve software resources that are used to support FAIRification. Overall, these BYODs intend to foster collaboration between different types of stakeholders involved in data management, curation, and reuse (e.g. domain experts, trainers, developers, data owners, data analysts, FAIR experts). The BYODs also serve as an opportunity to learn what kind of support for FAIRification is needed from different communities and to develop teaching materials based on practical examples and experience. In this paper, we detail the three different structures of the BYODs and describe examples of early BYODs related to plant breeding data, and rare disease registries and biobanks, which have shaped the structure of the workshops. We discuss the latest insights into making BYODs more productive by leveraging our almost ten years of training experience in these workshops, including successes and encountered challenges. Finally, we examine how the participants’ feedback has motivated the research on FAIR, including the development of workflows and software.

CGG toolkit: Software components for computational genomics

Public-domain availability for bioinformatics software resources is a key requirement that ensures long-term permanence and methodological reproducibility for research and development across the life sciences. These issues are particularly critical for widely used, efficient, and well-proven methods, especially those developed in research settings that often face funding discontinuities. We re-launch a range of established software components for computational genomics, as legacy version 1.0.1, suitable for sequence matching, masking, searching, clustering and visualization for protein family discovery, annotation and functional characterization on a genome scale. These applications are made available online as open source and include MagicMatch, GeneCAST, support scripts for CoGenT-like sequence collections, GeneRAGE and DifFuse, supported by centrally administered bioinformatics infrastructure funding. The toolkit may also be conceived as a flexible genome comparison software pipeline that supports research in this domain. We illustrate basic use by examples and pictorial representations of the registered tools, which are further described with appropriate documentation files in the corresponding GitHub release.

Boosting Attack Detection Capabilities in Multi-Tenant Distributed Systems via Meta-Ensemble Classifiers and Weighted Averaging

Multi-tenant distributed systems are a great way to share resources and scale performance, but they come with their share of security issues due to the introduction of more than one client on the cloud. Sharing of hardware and software resources among tenants gives rise to vulnerabilities and malicious tenants can misuse this shared data to launch attacks on other tenants. While efforts have traditionally focused on building secure network architectures, it is impossible to create a completely secure system due to its open-ended nature. This paper explores ways to detect malicious tenants on the cloud using machine learning algorithms. This paper proposes an ensemble-based meta-classifier to predict the probability of attack instantiation based on certain system parameter values. Additionally, this paper creates a dataset for analysis purposes and address the class imbalance problem often found in this domain where attack instances are rare. Satisfactory results were produced to distinguish between non attach and attack instances.

Deep learning-based DOA estimation for hybrid massive MIMO receive array with overlapped subarrays

As massive MIMO is a key technology in the future sixth generation (6G), the large-scale antenna arrays are widely considered in direction-of-arrival (DOA) estimation for they can provide larger aperture and higher estimation resolution. However, the conventional fully digital architecture requires one radio-frequency (RF) chain per antenna, and this is challenging for the high hardware costs and much more power consumption caused by the large number of RF chains. Therefore, an overlapped subarray (OSA) architecture-based hybrid massive MIMO array is proposed to reduce the hardware costs, and it can also have better DOA estimation accuracy compared to non-overlapped subarray (NOSA) architecture. The simulation results also show that the accuracy of the proposed OSA architecture has 6^{circ } advantage over the NOSA architecture with signal-to-noise ratio (SNR) at 10 dB. In addition, to improve the DOA estimation resolution, a deep learning (DL)-based estimator is proposed by combining convolution denoise autoencoder (CDAE) and deep neural network (DNN), where CDAE can remove the approximation error of sample covariance matrix (SCM) and DNN is used to perform high-resolution DOA estimation. From the simulation results, CDAE-DNN can achieve the accuracy lower bound at textrm{SNR}=-8 dB and the number of snapshots N=100, this means it has better performance in poor communication situation and can save more software resources compared to conventional estimators.

Neutralising the digital divide: is blended learning a viable solution?

The digital divide (DD), which refers to the gap resulting from unequal access to digital technology hardware, software and ideological-ware resources, arises from disparities in accessing, material and physical resources that enable internet access. In the contemporary world, this divide extends beyond internet access to include the ability to manipulate educational technologies in the knowledge building process. Therefore, the installation of the internet infrastructure in communities should not be considered as the sole facility to access. In attempting to curb the DD, blended learning is seen to be a possible viable option. It is against this backdrop that this article sought to explore the role of blended learning in neutralising DD. This qualitative case study employed the resources and appropriation theory as a lens to analyse DD as a result of societal inequalities and unequal distribution of resources. The community of Inquiry (COI) framework was also used as a theoretical lens to guide the implementation of social and cognitive knowledge-building in a blended learning context. The reported study employed purposive sampling involving 26 participants who were the recipients of blended learning in one institution of higher learning (HEI) in Lesotho. Data were generated through reflective journals and one-on-one semi-structured interviews, and guided analysis was used to interpret the generated data. The findings established that blended learning has the capacity to neutralise DD, as it affords students the flexibility to design and engage in individualised learning experiences through both offline and online modes of teaching and learning, thereby meeting their access needs. The recommendation proposed in this article, thus, is for HEIs to adopt blended learning to eliminate categorical inequalities and social divisions in education, ideally promoting equilibrated inclusion of individuals from diverse socio-economic backgrounds in the teaching and learning process.

Sustainable Management of International Partnerships for Cultural Heritage Digitization in Brazil

The demand for digitized cultural heritage has increased over the last few decades; digitization is indeed considered a powerful means to preserve and enhance cultural heritage and make it accessible to the wider public for education and research purposes. However, digitizing cultural heritage is a complex process, requiring specific competencies, skills, software, technologies, and, therefore, human and financial resources. Cultural organizations are therefore rethinking their traditional business models, often deciding to outsource their digitization projects or implementing PPPs—public–private partnerships. This is particularly evident in developing countries, where it is also challenging to find the required resources locally and international cooperation is sometimes necessary. However, international PPPs for the digitization of cultural heritage present several unsustainable aspects. There is therefore a need for a deeper understanding of which practices should be implemented to sustainably manage these collaborations. This paper aims to investigate this topic using a case study analysis of two international PPPs for the digitization of cultural heritage in Brazil. The analysis highlights relevant managerial choices that led these projects to positively impact local social, economic, and environmental development, thus bringing early insights to advance the academic and practice discussions on the above-mentioned topic.

Cybersecurity Risk Assessments within Critical Infrastructure Social Networks

Cybersecurity social networking is a new scientific and engineering discipline that was interdisciplinary in its early days, but is now transdisciplinary. The issues of reviewing and analyzing of principal tasks related to information collection, monitoring of social networks, assessment methods, and preventing and combating cybersecurity threats are, therefore, essential and pending. There is a need to design certain methods, models, and program complexes aimed at estimating risks related to the cyberspace of social networks and the support of their activities. This study considers a risk to be the combination of consequences of a given event (or incident) with a probable occurrence (likelihood of occurrence) involved, while risk assessment is a general issue of identification, estimation, and evaluation of risk. The findings of the study made it possible to elucidate that the technique of cognitive modeling for risk assessment is part of a comprehensive cybersecurity approach included in the requirements of basic IT standards, including IT security risk management. The study presents a comprehensive approach in the field of cybersecurity in social networks that allows for consideration of all the elements that constitute cybersecurity as a complex, interconnected system. The ultimate goal of this approach to cybersecurity is the organization of an uninterrupted scheme of protection against any impacts related to physical, hardware, software, network, and human objects or resources of the critical infrastructure of social networks, as well as the integration of various levels and means of protection.

A genome-wide association study reveals that epistasis underlies the pathogenicity of Pectobacterium.

Pectobacterium spp. are important bacterial pathogens that cause soft rot symptoms in various crops. However, their mechanism of pathogenicity requires clarity to help control their infections. Here, genome-wide association studies (GWAS) were conducted by integrating genomic data and measurements of two phenotypes (virulence and cellulase activity) for 120 various Pectobacterium strains in order to identify the genetic basis of their pathogenicity. An artificial intelligence-based software program was developed to automatically measure lesion areas on Chinese cabbage, thereby facilitating accurate and rapid data collection for virulence phenotypes for use in GWAS analysis. The analysis discovered 428 and 158 loci significantly associated with Pectobacterium virulence (lesion area) and cellulase activity, respectively. In addition, 1,229 and 586 epistasis loci pairs were identified for the virulence and cellulase activity phenotypes, respectively. Among them, the AraC transcriptional regulator exerted epistasis effects with another three nutrient transport-related genes in pairs contributing to the virulence phenotype, and their epistatic effects were experimentally confirmed for one pair with knockout mutants of each single gene and double gene. This study consequently provides valuable insights into the genetic mechanism underlying Pectobacterium spp. pathogenicity. IMPORTANCE Plant diseases and pests are responsible for the loss of up to 40% of food crops, and annual economic losses caused by plant diseases reach more than $220 billion. Fighting against plant diseases requires an understanding of the pathogenic mechanisms of pathogens. This study adopted an advanced approach using population genomics integrated with virulence-related phenotype data to investigate the genetic basis of Pectobacterium spp., which causes serious crop losses worldwide. An automated software program based on artificial intelligence was developed to measure the virulence phenotype (lesion area), which greatly facilitated this research. The analysis predicted key genomic loci that were highly associated with virulence phenotypes, exhibited epistasis effects, and were further confirmed as critical for virulence with mutant gene deletion experiments. The present study provides new insights into the genetic determinants associated with Pectobacterium pathogenicity and provides a valuable new software resource that can be adapted to improve plant infection measurements.

Virtual Teaching and Learning Platform for Caregivers of Children with Autism

This paper aims to discuss the critical aspects and necessary elements of virtual teaching and learning for children with autism. Given the challenges faced by parents and caregivers in supporting the education of children with autism, it becomes crucial to develop effective strategies and platforms that ensure their educational progress. While efforts have been made to provide equal educational opportunities for children with autism, there is a lack of research on digital learning specifically tailored to their needs, and limited availability of accessible learning software resources. Therefore, it is essential to conduct a review of the key features and essential components of VTL platforms that support caregivers, as well as examine the integration techniques to facilitate VTL. This study employs a literature review methodology, involving a systematic search and selection of relevant articles from academic databases, followed by an analysis and synthesis of the findings to explore the utilization of ICT technology in VTL for children with autism. In addition, this review aims to assist future researchers by presenting a proposed VTL platform, thereby contributing to the design and development of effective VTL platforms for this unique group of learners.