Application Running Research Articles

Review on Academia Hub: Android Application for Student Attendance System

Until today, most lecturers in universities are found still using the conventional methods of taking students’ attendance either by calling out the student names or by passing around an attendance sheet for students to sign confirming their presence. In addition to the time-consuming issue, such method is also at higher risk of having students cheating about their attendance, especially in a large classroom. Therefore, a method of taking attendance by employing an application running on the Android platform is proposed in this paper. This application, once installed can be used to download the students list from a designated web server. Based on the downloaded list of students, the device will then act like a scanner to scan each of the student cards one by one to confirm and verify the student’s presence. The device’s camera will be used as a sensor that will read the barcode printed on the students’ cards. The updated attendance list is then uploaded to an online database and can also be saved as a file to be transferred to a PC later on. This system will help to eliminate the current problems, while also promoting a paperless environment at the same time. Since this application can be deployed on lecturers’ own existing Android devices, no additional hardware cost is required

Perancangan Multimedia Informasi Iklan Layanan Masyarakat “Domestic Abuse” Di Dinas Pemberdayaan Perempuan Perlindungan Anak Dan Keluarga Berencana Jawa Barat

Domestic abuse is a social problem in Indonesia that always be inherent and not easy to deal with, the rate of domestic abuse exploded when pandemic happen in Indonesia. in West Java alone there already 2000 case about domestic abuse that already registered. This number can be pressed if society have the courage and awareness about domestic abuse among them, as a victim or as a witness of the abuse. This multimedia application was designed for facilitate the socialization process of domestic abuse in order to cultivate courage in society to report if they see someone they know is a victim of domestic abuse. So, an information multimedia application of domestic abuse public service advertisements with a case study at the West Java Women's Empowerment, Child Protection and Family Planning Office was created. The methodology used is Multimedia Development Life Cycle (MDLC) that have 6 stages (concept, design, material collecting, assembly, testing, and distribution). The , multimedia application of domestic abuse public service advertisements was designed according to users need obtained from observation and implemented using Adobe Animate CC 2019 with Action Script 3.0 programming language.the testing of this application is using black box testing method show that this application running smoothly and fit to what the user wants. The result of this testing show that the average of the testing result from 3 category (design, feature, and user satisfaction) with 12 test parameters is 4,39 (87,8%).

Comparison of Cloud Computing, SaaS, SOA and Microservices

A network application is an application that runs on a single host and facilitates communication with another application running on a different computer or host. Numerous network applications have been introduced, including cloud computing, SaaS, SOA, and microservices. However, these technologies have often been used interchangeably, leading to confusion among developers and researchers. Therefore, the objective of this study is to review and compare the available network applications, specifically cloud computing, Software as a Service (SaaS), Service Oriented Architecture (SOA), and microservices. This study conducts a comparative analysis by examining several important criteria such as definition, type, language, interoperability, characteristics, and examples. By providing clear and precise definitions for each technology, the study aims to clarify their distinctions and appropriate usage contexts. The findings successfully establish the correct terminology for each technology and offer detailed discussions on the specific platforms and situations where each is most suitable. This comprehensive review serves as a valuable resource for developers and researchers seeking to navigate the complexities of modern network applications.

Check-QZP: A Lightweight Checkpoint Mechanism for Deep Learning Frameworks

In deep learning (DL) frameworks, a checkpoint operation is widely used to store intermediate variable values (e.g., weights, biases, and gradients) on storage media. This operation helps to reduce the recovery time of running a machine learning (ML) model after sudden power failures or random crashes. However, the checkpoint operation can stall the overall training step of the running model and waste expensive hardware resources by leaving the GPU in idle sleep during the checkpoint operation. In addition, the completion time of the checkpoint operation is unpredictable in cloud server environments (e.g., AWS and Azure) because excessive I/O operations issued by other running applications interfere with the checkpoint operations in the storage stacks. To efficiently address the above two problems, we carefully designed Check-QZP, which reduces the amount of data required for checkpoint operations and parallelizes executions on the CPU and GPU by understanding the internal behaviors of the training step. For the evaluation, we implemented Check-QZP and compared it with the traditional approach in real-world multi-tenant scenarios. In the evaluation, Check-QZP outperformed the baseline in all cases in terms of the overall checkpoint time and the amount of data generated by the checkpoint operations, reducing them by up to 87.5% and 99.8%, respectively. In addition, Check-QZP achieved superior training speeds compared to the baseline.

A dual wave structure triboelectric sensor for heart rate and exercise monitoring

Recently, research on wearable devices for physiological exercise monitoring has garnered significant attention. Here, we propose a dual wave-structured triboelectric nanogenerator (DW-TENG) integrated with a cotton cloth, developed for smart running applications. The DW-TENG sensor leverages a flexible wave triboelectric layer composed of polydimethylsiloxane and silicone, with a copper electrode layer between them for sensing. This structure allows for customizable pressure sensitivity by adjusting the silicone hardness. Experimental results show that the DW-TENG achieves a sensitivity of 0.4 V kPa−1, with response and recovery times of 75 and 90 ms, respectively. The sensor effectively measures heart rate changes during various physical activities, including walking, running, and jumping. Electrical performance tests reveal that the DW-TENG’s output is significantly influenced by the silicone hardness, operational frequency, and microstructure height. The DW-TENG sensor demonstrates high durability and stability, maintaining consistent voltage output over 40 000 cycles. This research highlights the potential of the DW-TENG in multifunctional physiological and physical activity monitoring, providing real-time data on respiratory patterns, heart rate, and movement dynamics, thus enhancing athletic training, performance assessment, and health monitoring.

Evaluating Mixed Reality Technology for Enhancing Art Pedagogy

The lack of interest among students in studying art, particularly the traditional Indonesian art form of batik, poses a significant challenge for educational institutions. Despite its cultural significance, the education sector lacks effective strategies to introduce and enhance students' interest in batik within the art curriculum. Several consequences can arise if the education sector fails to implement strategic measures to address this issue promptly. This could lead to a gradual erosion of cultural heritage and a loss of artistic traditions passed down through generations, and students may miss out on valuable opportunities for self-expression and cultural exploration. This study addresses this issue by leveraging mixed reality and gamification in a batik creation application. This innovative approach not only enhances the pedagogy of art education but also aims to revive cultural interest. The study employs Software Testing and PIECES to evaluate user experiences, emphasizing user comfort and smooth interactions. By assessing the application with tools like Unity Profiler and Hololens 2 performance testing, the study ensures an optimal user experience, contributing to the broader goal of preserving Indonesia's cultural heritage through innovative and accessible educational solutions. The results fall within the range of 4.04 to 4.24, categorizing user satisfaction as "satisfied" and the application running at an optimal 60 frames per second (FPS). This implies that users responded positively to the application, indicating that implementing mixed reality technology in batik learning provides a satisfying experience.

Performance analysis of selected database management systems

The article presents the results of performance tests of database management systems. In order to conduct the tests, an application running in Java environment and using an ORM tool such as Hibernate for communication with the database was used. The tests were carried out for test scenarios such as CRUD operations, join queries, aggregate functions, and filter conditions in queries. The DBMSes used for testing were MySQL, PostgreSQL and H2. Performance analysis looked at the execution time of operations, RAM usage and CPU load. Additionally, tests were carried out for different sizes of user groups using the application. PostgreSQL proved to be the best choice for complex operations.

Experimental Study of Long Short-Term Memory and Transformer Models for Fall Detection on Smartwatches.

Falls are the second leading cause of unintentional injury deaths worldwide. While numerous wearable fall detection devices incorporating AI models have been developed, none of them are used successfully in a fall detection application running on commodity-based smartwatches in real time. The system misses some falls, and generates an annoying amount of False Positives for practical use. We have investigated and experimented with an LSTM model for fall detection on a smartwatch. Even though the LSTM model has high accuracy during offline testing, the good performance of offline LSTM models cannot be translated to the equivalence of real-time performance. Transformers, on the other hand, can learn long-sequence data and patterns intrinsic to the data due to their self-attention mechanism. This paper compares three variants of LSTM and two variants of Transformer models for learning fall patterns. We trained all models using fall and activity data from three datasets, and the real-time testing of the model was performed using the SmartFall App. Our findings showed that in the offline training, the CNN-LSTM model was better than the Transformer model for all the datasets. However, the Transformer is a preferable choice for deployment in real-time fall detection applications.

A comparative analysis of game experience in treadmill running applications

Despite the growing popularity of treadmill running apps, comparative analyses between exergames and traditional running simulators in terms of user experience are scarce. This study aims to fill this gap by examining user experiences across three different treadmill running apps: Zwift (a running simulator), Ring Fit Adventure (a Nintendo Switch game), and Fitoon (a mobile-specific treadmill game). Using unique interaction mechanisms-pedometer, leg-mounted controller with Ring-Con, and smartwatch, respectively, each app is evaluated through the In-Game version of the Game Experience Questionnaire. Results indicate that exergames, particularly Fitoon, significantly improve Competence, Immersion, and game flow compared to traditional treadmill running activities. However, contrary to expectations, the use of a smartwatch for interaction did not significantly decrease levels of Negative Affect. This finding underscores the complexity of the relationship between interaction mechanisms and their impact on user emotions within treadmill running applications. By providing a comprehensive analysis of user experiences, this study provides insight into the potential benefits and limitations of different interaction systems and platforms, providing valuable information for the development of more emotionally engaging and rewarding treadmill running apps. crucial.

Perancangan Sistem Informasi Automatic Capture Tool dengan Metode Analisa Cost Benefit

Technology has an impact on the evolution of the business world, which can affect how to plan, control and evaluate business activities, as is the case with Adira Finance. Adira Finance has used the Monitoring Application to monitor the running application system, namely the ELK Tools (Elasticsearch Logstash and Kibana). ELK can capture existing data on the server, be it CPU usage, database, network, and so on. ELK can provide a warning if there is a failure or error in the application system used. However, the current solution team only analyzes data after a failure or error, cannot analyze data before the incident. For this reason, implementation of automation capture is carried out using Selenium WebDriver to assist in capturing automatic monitoring results earlier before system failure occurs. The analysis was carried out by applying the cost benefit analysis method. The result of this implementation is a bot that can automatically capture and send the results to the telegram group in Adira Finance. Companies can consider whether the implementation of this automation for repairs or improvements to the monitoring system performance management is acceptable or not

Обеспечение функционирования графических GLX приложений на промышленном оборудовании с использованием API EGL

This paper discusses the operation of engineering software on systems with graphics adapter drivers that provide limited to no support for certain graphics subsystems of Linux OS. The paper demonstrates that software with GLX API-based visualization subsystem needs modification to be ported to the embedded systems using graphics accelerators with drivers that support only the EGL API. The purpose of the study is to develop approaches for enabling the operation of software on industrial equipment and utilizing the GLX API via the EGL API of the Linux-based graphics subsystem. The paper discussed the method for translating GLX API calls to the EGL API and its applicability. A new algorithm has been developed for organizing interaction between user applications and the Linux OS graphics subsystem, which allows running applications with the GLX API in the absence of DRI support by the graphics accelerator driver. The correctness of the algorithm’s operation has been tested and compared with the results of the tests of open drivers with DRI2 support. The findings will make it possible to reduce the resources needed to support individual graphics driver subsystems and make a smooth transition to using the EGL API in the embedded systems.

Abstract PO2-28-06: An on-line deep learning decision support tool, iBRISK, aimed at improving breast cancer risk estimation and reducing unnecessary biopsies for BI-RADS 4 patients

Abstract Probability of malignancy (POM) for Breast Imaging Reporting and Data System (BI-RADS) category 4 designated breast lesions ranges from 2% – 95% and contributes to a high unnecessary biopsy rate. This is as most clinicians often stick to the biopsy option to rule in or out breast cancer early; withholding biopsy could be risky, and biopsies of BI-RADS 4 lesions serve as a quality metric and performance standard. At 21.1%, biopsy-proven positive predictive value (PPV3) rates for BI-RADS 4 have not improved for decades, translating to high false-positive rates of mammography. Unnecessary biopsies are a big issue in the management of BI-RADS 4 lesions with negative implications including increased medical costs, healthcare wastes, unnecessary psychological burdens to the patients, and potential complications and risks. Objectives 1. Optimize the precision breast cancer risk assessment tool, iBRISK, that utilizes artificial intelligence (AI) technologies, including natural language processing (NLP), image processing, and deep learning, with clinical risk factors and imaging features. 2. Develop a user-friendly web interface for iBRISK to facilitate clinicians or insurers in estimating cancer risk and making informed biopsy decisions for BI-RADS 4 lesions. Methods Our intelligent-augmented breast cancer risk calculator (iBRISK) model was trained on multimodal data collected from 10,778 patients, including demographic factors, historical and clinical characteristics, mammographic features, and pathologic signatures. We validated iBRISK using 4,200 patients from multiple leading hospitals, including Houston Methodist Neal Cancer Center, the University of Texas MD Anderson Cancer Center, and the University of Texas Health San Antonio MD Anderson Mays Cancer Center. The iBRISK was connected to a backend server which is linked to a frontend web user interface using technologies like Hypertext Preprocessor (PHP) for the backend application running on an APACHE HTTP server and React-JavaScript for the front-end web application that communicates with the backend using Representational State Transfer Application Programming Interface (RESTful API) and JavaScript Object Notation (JSON) format. The communication was secured using Secure Sockets Layer (SSL) encryption. Results The iBRISK model demonstrated high sensitivity in malignancy prediction and achieved an accuracy of 89.5%, area under the receiver operating characteristic curve of 0.93 (95% CI: 0.92-0.95), sensitivity of 100%, and specificity of 81%. Only 0.16% of lesions determined to have low POM by the model were malignant. Our multi-center study shows that iBRISK achieves at least 50% reduction in unnecessary biopsies of BI-RADS 4 cases. Data elements for the required 20 features are entered into the interface using a variety of imputation methods including direct text, dropdown menus and radio button selections. The user-friendly web interface provides risk scores (0 – 1), risk levels (low, medium, and high), and associated biopsy recommendations. Conclusion The user-friendly iBRISK web interface is proposed as an adjunct to the BI-RADS system, enhancing the precision of BI-RADS 4 lesion cancer risk stratification. It is expected to reduce unnecessary biopsies, lower health costs, and enhance the quality of health care. This approach aims to tackle a critical issue in breast cancer diagnosis by leveraging advanced AI technologies and big data and providing clinicians with a tool to make more informed and precise biopsy decisions for BI-RADS 4 lesions. Citation Format: Chika Ezeana, Xiaohui Yu, Zhihao Wan, Tiancheng He, Tejal Patel, Virginia Kaklamani, Maryam Elmi, Erika Brigmon, Pamela Otto, Kenneth Kist, Lin Wang, Joe Ensor, Heather Speck, Ya-Chen Shih, Bumyang Kim, I-Wen Pan, David Spak, Wei Yang, Jenny Chang, Stephen Wong. An on-line deep learning decision support tool, iBRISK, aimed at improving breast cancer risk estimation and reducing unnecessary biopsies for BI-RADS 4 patients [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-28-06.

Development of Method for the Measurement of Dermal Exposure on a Lifelike Cow Dummy to Assess the Risk of Using a Urease Inhibitor (Atmowell®) to Reduce NH3 Emissions in Cattle Farming

Up to 58% of NH3 emissions can be reduced through the use of the urease inhibitor Atmowell® in cattle farming. Automated manure scraper and drag hose systems should be used to apply urease inhibitors (UIs) to stable floors. Proof of safe use is also needed. A risk assessment of the urease inhibitor PPDA was conducted utilising estimated and calculated exposure data along with established and verified model calculation tools. Risk assessment models can be improved using measured dermal exposure data. The fluorescent dye pyranine and a Tyvek® collector were used to measure exposure. Tyvek® was attached to a lifelike cow dummy. Regarding the drag hose system, two worst-case scenarios were considered: over the cow and passing the cow. Regarding the robot application system, a 0 m frontal scenario was considered. The over the cow scenario exhibited the highest dermal exposure, with 1.5 mg of PPDA/cow per application run. The robot scenario exhibited the smallest amount, with 0.8 mg of PPDA/cow per application run. The risk of using PPDA was already excluded by model calculation tools in a risk assessment. Compared with the estimated and calculated dermal exposure values, the measured dermal exposure levels were reduced by a factor of two to six.

Survey on Quality of Experience Evaluation for Cloud-Based Interactive Applications

A cloud-based interactive application (CIA) is an application running in the cloud with stringent interactivity requirements, such as remote desktop and cloud gaming. These services have experienced a surge in usage, primarily due to the adoption of new remote work practices during the pandemic and the emergence of entertainment schemes similar to cloud gaming platforms. Evaluating the quality of experience (QoE) in these applications requires specific metrics, including interactivity time, responsiveness, and the assessment of video- and audio-quality degradation. Despite existing studies that evaluate QoE and compare features of general cloud applications, systematic research into QoE for CIAs is lacking. Previous surveys often narrow their focus, overlooking a comprehensive assessment. They touch on QoE in broader contexts but fall short in detailed metric analysis. Some emphasise areas like mobile cloud computing, omitting CIA-specific nuances. This paper offers a comprehensive survey of QoE measurement techniques in CIAs, providing a taxonomy of input metrics, strategies, and evaluation architectures. State-of-the-art proposals are assessed, enabling a comparative analysis of their strengths and weaknesses and identifying future research directions.

A Scalable Monitoring System for Software Defined Networks

Monitoring functionality is an essential element of any network system. Traditional monitoring solutions are mostly used for manual and infrequent network management tasks. Software-defined networks (SDN) have emerged with enabled automatic and frequent network reconfigurations. In this paper, a scalable monitoring system for SDN is introduced. The proposed system monitors small, medium, and large-scale SDN. Multiple instances of the proposed monitoring system can run in parallel for monitoring many SDN slices. The introduced monitoring system receives requests from network management applications, collects considerable amounts of measurement data, processes them, and returns the resulting knowledge to the network management applications. The proposed monitoring system slices the network (switches and links) into multiple slices. The introduced monitoring system concurrently monitors applications for various tenants, with each tenant's application running on a dedicated network slice. Each slice is monitored by a separate copy of the proposed monitoring system. These copies operate in parallel and are synchronized. The scalability of the monitoring system is achieved by enhancing the performance of SDN. In this context, scalability is addressed by increasing the number of tenant applications and expanding the size of the physical network without compromising SDN performance.

PArtNNer: Platform-Agnostic Adaptive Edge-Cloud DNN Partitioning for Minimizing End-to-End Latency

The last decade has seen the emergence of Deep Neural Networks (DNNs) as the de facto algorithm for various computer vision applications. In intelligent edge devices, sensor data streams acquired by the device are processed by a DNN application running on either the edge device itself or in the cloud. However, “edge-only” and “cloud-only” execution of State-of-the-Art DNNs may not meet an application’s latency requirements due to the limited compute, memory, and energy resources in edge devices, dynamically varying bandwidth of edge-cloud connectivity networks, and temporal variations in the computational load of cloud servers. This work investigates distributed (partitioned) inference across edge devices (mobile/end device) and cloud servers to minimize end-to-end DNN inference latency. We study the impact of temporally varying operating conditions and the underlying compute and communication architecture on the decision of whether to run the inference solely on the edge, entirely in the cloud, or by partitioning the DNN model execution among the two. Leveraging the insights gained from this study and the wide variation in the capabilities of various edge platforms that run DNN inference, we propose PArtNNer , a platform-agnostic adaptive DNN partitioning algorithm that finds the optimal partitioning point in DNNs to minimize inference latency. PArtNNer can adapt to dynamic variations in communication bandwidth and cloud server load without requiring pre-characterization of underlying platforms. Experimental results for six image classification and object detection DNNs on a set of five commercial off-the-shelf compute platforms and three communication standards indicate that PArtNNer results in 10.2× and 3.2× (on average) and up to 21.1× and 6.7× improvements in end-to-end inference latency compared to execution of the DNN entirely on the edge device or entirely on a cloud server, respectively. Compared to pre-characterization-based partitioning approaches, PArtNNer converges to the optimal partitioning point 17.6× faster.

An Operative IoT Grounded AEEBLR (Ant-Founded Efficient Energy and Balanced Load Routing) Method for Path Conjunction in Mobile Ad Hoc Networks Approach

An architecture for a wireless network that is constantly developing, decentralized, and multi-hop is called a mobile ad hoc network. MANETs are able to function in many different contexts where regular networks are unable. As can be seen from the advantages listed above, these networks are well-suited for a wide variety of applications, some of which include military and commercial use, as well as applications relating to disaster management, rescue operations, and defense. Energy conservation is a standard factor that indicates the overall network lifetime in mobile ad hoc networks that operate on rechargeable or replaceable battery. This is because usage, battery power consumption in relation to transmission range, type of application running on each device, location, and other influences all play a part in determining the overall network lifetime. An earlier study used a method called ant colony optimization, which is a form of swarm intelligence enthused by the activity of foraging ants in colonies. The best possible travel plan was found using this strategy. Current MANETS routing systems face difficulties in load balancing and energy efficiency that must be overcome if optimal path convergence is to be achieved. When deciding on the next hop node, the IoT based AEEBLR method is recommended. The latency, energy consumption, congestion, and connection quality are all taken into account before making a final decision. The likelihood of selecting the next-hop node as the neighbor node is determined using these metrics. It is the following hop's probability that determines which ant agent goes forward and which goes backward. This paves the door for the creation of many paths, from which the most effective might be chosen for transmission. The results of the implementation show that the suggested AEEBLR technique outperforms the existing AESR approach when the number of packets, the number of nodes, and the mobility of nodes are all varied.

Analysis of the Possibilities of Carrying Out Attacks on the Functions of Transferring Control to Operating System Console Using Active Intelligence Methods

This paper researches the possibility of conducting attacks on the console control transfer functions using active intelligence methods. The research employs a comprehensive approach involving ports scanning, directories searching, parameters modifying, and credentials searching based on a user dictionary. Additionally, the study involves the development of a software tool designed to detect vulnerabilities in network nodes. The software developed within the framework of this study is delivered in the form of two modules, the first module contains the main program with the mechanisms implemented in it to indicate the possibility of attacks, with an emphasis on current web applications and services. Checking for the possibility of an attack for any network node is that first a list of requests is compiled, the purpose of which is to identify weaknesses of a web application running on the server, and a list of expected responses from the server is also compiled for these requests. After that request goes to the server, the program waits for responses from the server, and if the expected responses from the compiled list coincide with the actual ones, then this fact signals the possibility of an attack on the web application. The second module stores localization dictionaries responsible for the presence of two interface languages in the program – Russian and English. The result of this work is the MaxNetScanner2022 software, which identifies the possibility of an attack on the system control transfer functions using active intelligence tools.

Multi-objective cost-aware bag-of-tasks scheduling optimization model for IoT applications running on heterogeneous fog environment

Recently introduced by CISCO, the fog computing paradigm extends cloud-based computing services near the Internet of Things (IoT) devices to serve their applications, aiming to increase performance. This new computing paradigm tries to meet the requirements of emerging IoT applications, which mostly are geographically distributed and location-aware, low-cost, and delay-sensitive. One of the frequently applied applications is a bag-of-tasks (BoT) of IoT applications, each of which includes several independent tasks. However, inefficient task scheduling approaches for parallel executions may degrade the delivered quality of service (QoS) to users and also increase the providers’ total cost of ownership (TCO). The reliable execution commensurate with users’ service level agreement (SLA) and affordable services tailored to their budget at the same time is favorable for both users and fog service providers because the highly reliable execution is a reputational metric that increases the users’ trust and adherence. To this end, this paper formulates the task scheduling for the execution of BoT in IoT applications to a multi-objective optimization problem with execution time, costs and reliability perspectives. To measure total costs, both the execution cost and monetary cost models are presented. To measure the resource reliability, the new scheduling failure factor (SFF) metric is also presented, which is a kind of cost parameter. To solve this combinatorial NP-Hard problem, a multi-objective cost-aware discrete grey wolf optimization-based algorithm (MoDGWA) is proposed. To verify the performance of MoDGWA, diverse scenarios were conducted and the performance of the proposed algorithm was compared against other state-of-the-arts. The extensive simulation results prove the average dominance of MoDGWA, and it has 0.55 %, 7.28 %, 10.20 %, and 45.83 % reduction against other state-of-the-art in terms of makespan, ToC, TSFF, and the cost score respectively. Note that, the implementation of the MoDGWA is available on https://github.com/mirsaeid123/Mirsaeid.

Extended Reality Telemedicine Collaboration System Using Patient Avatar Based on 3D Body Pose Estimation.

Recent advances in extended reality (XR) technology have opened the possibility of significantly improving telemedicine systems. This is primarily achieved by transferring 3D information about patient state, which is utilized to create more immersive experiences on VR/AR headsets. In this paper, we propose an XR-based telemedicine collaboration system in which the patient is represented as a 3D avatar in an XR space shared by local and remote clinicians. The proposed system consists of an AR client application running on Microsoft HoloLens 2 used by a local clinician, a VR client application running on the HTC vive Pro used by a remote clinician, and a backend part running on the server. The patient is captured by a camera on the AR side, and the 3D body pose estimation is performed on frames from this camera stream to form a 3D patient avatar. Additionally, the AR and VR sides can interact with the patient avatar via virtual hands, and annotations can be performed on a 3D model. The main contribution of our work is the use of 3D body pose estimation for the creation of a 3D patient avatar. In this way, 3D body reconstruction using depth cameras is avoided, which reduces system complexity and hardware and network resources. Another contribution is the novel architecture of the proposed system, where audio and video streaming are realized using WebRTC protocol. The performance evaluation showed that the proposed system ensures high frame rates for both AR and VR client applications, while the processing latency remains at an acceptable level.