Utility In Applications Research Articles

Similar Data Points Identification with LLM: A Human-in-the-Loop Strategy Using Summarization and Hidden State Insights

This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This approach leverages the advanced comprehension and generative capabilities of LLMs, offering a scalable and efficient strategy for similarity identification across diverse datasets. We demonstrate the effectiveness of our method in identifying similar data points on multiple datasets. Additionally, our approach enables non-technical domain experts, such as fraud investigators or marketing operators, to quickly identify similar data points tailored to specific scenarios, demonstrating its utility in practical applications. In general, our results open new avenues for leveraging LLMs in data analysis across various domains.

Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks.

Graph neural networks (GNNs) tend to suffer from high computation costs due to the exponentially increasing scale of graph data and a large number of model parameters, which restricts their utility in practical applications. To this end, some recent works focus on sparsifying GNNs (including graph structures and model parameters) with the lottery ticket hypothesis (LTH) to reduce inference costs while maintaining performance levels. However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where vast redundancy exists. To overcome the above limitations, we propose a comprehensive graph gradual pruning framework termed CGP. This is achieved by designing a during-training graph pruning paradigm to dynamically prune GNNs within one training process. Unlike LTH-based methods, the proposed CGP approach requires no retraining, which significantly reduces the computation costs. Furthermore, we design a cosparsifying strategy to comprehensively trim all the three core elements of GNNs: graph structures, node features, and model parameters. Next, to refine the pruning operation, we introduce a regrowth process into our CGP framework, to reestablish the pruned but important connections. The proposed CGP is evaluated over a node classification task across six GNN architectures, including shallow models [graph convolutional network (GCN) and graph attention network (GAT)], shallow-but-deep-propagation models [simple graph convolution (SGC) and approximate personalized propagation of neural predictions (APPNP)], and deep models [GCN via initial residual and identity mapping (GCNII) and residual GCN (ResGCN)], on a total of 14 real-world graph datasets, including large-scale graph datasets from the challenging Open Graph Benchmark (OGB). Experiments reveal that the proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of the existing methods.

Graph-Based Semi-Supervised Learning with Bipartite Graph for Large-Scale Data and Prediction of Unseen Data

Recently, considerable attention has been directed toward graph-based semi-supervised learning (GSSL) as an effective approach for data labeling. Despite the progress achieved by current methodologies, several limitations persist. Firstly, many studies treat all samples equally in terms of weight and influence, disregarding the potential increased importance of samples near decision boundaries. Secondly, the detection of outlier-labeled data is crucial, as it can significantly impact model performance. Thirdly, existing models often struggle with predicting labels for unseen test data, restricting their utility in practical applications. Lastly, most graph-based algorithms rely on affinity matrices that capture pairwise similarities across all data points, thus limiting their scalability to large-scale databases. In this paper, we propose a novel GSSL algorithm tailored for large-scale databases, leveraging anchor points to mitigate the challenges posed by large affinity matrices. Additionally, our method enhances the influence of nodes near decision boundaries by assigning different weights based on their importance and using a mapping function from feature space to label space. Leveraging this mapping function enables direct label prediction for test samples without requiring iterative learning processes. Experimental evaluations on two extensive datasets (Norb and Covtype) demonstrate that our approach is scalable and outperforms existing GSSL methods in terms of performance metrics.

Development and Validation of a Mobile Phone Application for Measuring Knee Range of Motion.

Knee range of motion (ROM) is an important indicator of knee function. Outside the clinical setting, patients may not be able to accurately assess knee ROM, which may impair recovery following trauma or surgery. This study aims to validate a smartphone mobile application developed to measure knee ROM compared to visual and goniometer ROM measurements. A knee ROM Android mobile application was developed to measure knee ROM. Patients ≥ 18 years old presenting to an orthopaedic clinic with native knee complaints were approached to participate. Knee ROM was measured bilaterally by an arthroplasty-trained surgeon using (1) vision, (2) goniometer, and (3) the mobile application. Measurements were compared in flexion and extension using a one-way analysis of variance with post hoc Tukey test (alpha = 0.05). Eighty-four knee ROM measurements (40 left, 44 right) were obtained in 47 patients. Median Kellgren-Lawrence grade from available radiographs was grade 3. In flexion, mobile application (117.6 ± 14.7 degrees) measurements were not significantly different from visual (116.1 ± 13.6 degrees) or goniometer (116.2 ± 13.6 degrees) measurements. In extension, mobile application (4.8 ± 7.3 degrees) measurements were significantly different from visual (1.9 ± 4.1 degrees) measurements on post hoc analysis (p < 0.01), while no differences were present compared to goniometer (3.1 ± 5.8 degrees) measurements. Our study found that a mobile application for evaluating knee ROM was noninferior to goniometer-based measurements performed by an arthroplasty-trained surgeon. Future studies will investigate this application's utility in (1) remote patient care, (2) accelerating recovery during rehabilitation, (3) detecting early postoperative complications including arthrofibrosis, and (4) adding additional functionalities to the application to provide more detail-oriented descriptive analyses of patient knee function.

Heterogeneity in Li-S Batteries Resolved through Operando Synchrotron Diffraction Studies

Lithium-Sulfur (Li-S) batteries are promising candidates for electric vehicle applications due to their very high theoretical specific capacity (1670 mAh/g) and the tremendous availability and low cost of elemental sulfur. However, their practical capacity is substantially smaller (~1000 mAh/g) and their cycling performance is hindered by numerous technical challenges caused by issues on both cathode and anode sides of the system. While Li-S cells with extended cycling lifetimes can be built, they are typically only effective when using excess electrolytes and applied pressure, limiting their utility for practical applications. To gain deeper insights into the origin of missing capacity and the capacity fade of Li-S cells, we conducted operando studies on Li-S pouch cell batteries using synchrotron powder diffraction techniques. This approach enabled us to sensitively track the various crystalline phases involved in the cycling of Li-S batteries and to resolve a variety of inhomogeneities within cells that may affect their performance and lifetime.

Quaternization of a Triphenylamine-Based Conjugated Porous Organic Polymer to Immobilize PtCl62- for the Photocatalytic Reduction of 4-Nitrophenol.

Photocatalytic reduction of 4-nitrophenol (4-NP) for converting it to nontoxic 4-aminophenol (4-AP) is one of the most efficient approaches for removing toxic 4-NP. Using porous organic polymers (POPs) as the support to immobilize noble metal catalysts has exhibited remarkable reduction performance but is rarely reported. Herein, a cationic triphenylamine-based POP was synthesized by quaternization to immobilize PtCl62- to prepare an efficient photocatalyst named DCM-TPA-Pt for the reduction of 4-NP to 4-AP in the presence of NaBH4. Different from reported methods which realize immobilization by doping or complexing, the support and PtCl62- are combined through electrostatic interaction with milder reaction conditions to produce a photocatalyst in this work. DCM-TPA-Pt shows excellent photocatalytic reduction performance, reaching 99.9% conversion within 3 min, and its pseudo-first-order constant is 0.0305 s-1, surpassing most of the reported photocatalysts. Moreover, DCM-TPA-Pt also exhibits equal reduction efficiency after five continuous cycles, which highlights its potential utilization in practical applications.

Effect of Nb content on the mechanical properties of Nbx(MoTaW)(1-x) (x = 0.4, 0.55, and 0.7) refractory multicomponent alloys

The MoNbTaW refractory multicomponent alloy (RMCA) retains good yield strength up to 1873K, but limited plasticity and high density at room temperature impede its utility in practical applications. Thus, a unique alloy design approach based on composition modification was used to improve these properties. Among the four constituent elements of the MoNbTaW alloy, Nb has good plasticity and lower density; hence a series of alloys with varying Nb content, namely Nbx(MoTaW)(1-x) with x = 0.4, 0.55, and 0.7 (designated as Nb0.4, Nb0.55, and Nb0.7 in this manuscript), were processed using vacuum arc melting. X-ray diffraction results showed that all the alloys formed as single-phase with the body-centered cubic crystal structure. The microstructures of these RMCAs are dendritic in nature with segregation of elements that decreased with heat treatment. The hardness values showed a decrease as the Nb content increased. The compressive yield strength values are 1251, 1055, and 945 MPa, and those of fractured strain are 10, 22, and 33 % for Nb0.4(MoTaW)0.6, Nb0.55(MoTaW)0.45, and Nb0.7(MoTaW)0.3 respectively. The increase in plastic strain and toughness is due to the increment in the Nb concentration, which is directly interpreted as an enhancement in degree of plasticity. The average grain sizes of Nb0.4, Nb0.55, and Nb0.7 RMCAs are measured to be 86 μm, 106 μm and 145 μm respectively. It was observed that 36 % of the grains are above 100 μm for Nb0.4 alloy, whereas this fraction is increased to 49 % and 60 % for Nb0.55 and Nb0.7 alloys respectively, which indicates an increase in average grain size as well as fraction of coarser grains as the Nb content increases. Hence, the improvement in plasticity is attributed to the increase in the average grain size and broader grain distribution. Fracture surface analysis of all the compositions showed quasi-cleavage behavior. This study demonstrates that increasing the Nb concentration in the MoNbTaW RMCA enhances plasticity while decreasing density. In comparison to conventional niobium alloys like C103 and FS-85, the alloys of the present study had higher yield strength at the temperatures where the tests were carried out. The specific yield strength values of these alloys are found to be higher than commercially available Nb alloys.

Class conditioned text generation with style attention mechanism for embracing diversity

In the field of artificial intelligence and natural language processing (NLP), natural language generation (NLG) has significantly advanced. Its primary aim is to automatically generate text in a manner resembling human language. Traditional text generation has mainly focused on binary style transfers, limiting the scope to simple transformations between positive and negative tones or between modern and ancient styles. However, accommodating style diversity in real scenarios presents greater complexity and demand. Existing methods usually fail to capture the richness of diverse styles, hindering their utility in practical applications. To address these limitations, we propose a multi-class conditioned text generation model. We overcome previous constraints by utilizing a transformer-based decoder equipped with adversarial networks and style-attention mechanisms to model various styles in multi-class text. According to our experimental results, the proposed model achieved better performance compared to the alternatives on multi-class text generation tasks in terms of diversity while it preserves fluency. We expect that our study will help researchers not only train their models but also build simulated multi-class text datasets for further research.

Self-Assembled Block Copolymers as a Facile Pathway to Create Functional Nanobiosensor and Nanobiomaterial Surfaces.

Block copolymer (BCP) surfaces permit an exquisite level of nanoscale control in biomolecular assemblies solely based on self-assembly. Owing to this, BCP-based biomolecular assembly represents a much-needed, new paradigm for creating nanobiosensors and nanobiomaterials without the need for costly and time-consuming fabrication steps. Research endeavors in the BCP nanobiotechnology field have led to stimulating results that can promote our current understanding of biomolecular interactions at a solid interface to the never-explored size regimes comparable to individual biomolecules. Encouraging research outcomes have also been reported for the stability and activity of biomolecules bound on BCP thin film surfaces. A wide range of single and multicomponent biomolecules and BCP systems has been assessed to substantiate the potential utility in practical applications as next-generation nanobiosensors, nanobiodevices, and biomaterials. To this end, this Review highlights pioneering research efforts made in the BCP nanobiotechnology area. The discussions will be focused on those works particularly pertaining to nanoscale surface assembly of functional biomolecules, biomolecular interaction properties unique to nanoscale polymer interfaces, functionality of nanoscale surface-bound biomolecules, and specific examples in biosensing. Systems involving the incorporation of biomolecules as one of the blocks in BCPs, i.e., DNA-BCP hybrids, protein-BCP conjugates, and isolated BCP micelles of bioligand carriers used in drug delivery, are outside of the scope of this Review. Looking ahead, there awaits plenty of exciting research opportunities to advance the research field of BCP nanobiotechnology by capitalizing on the fundamental groundwork laid so far for the biomolecular interactions on BCP surfaces. In order to better guide the path forward, key fundamental questions yet to be addressed by the field are identified. In addition, future research directions of BCP nanobiotechnology are contemplated in the concluding section of this Review.

Interfacial engineering between carbon vacancies modified graphitic carbon nitride and CoAl-LDH formed heterojunctions for improved photocatalytic performance: Degradation pathway, DFT calculations, and mechanism insights

The construction of green, low-cost heterojunctions with interfacial interaction is crucial to enhance their photocatalytic performance and broaden their utility in practical applications. Here, we prepared CoAl-LDH/Carbon Nitride with carbon vacancies (Cv-CN) heterojunction by electrostatic self-assembly strategy to explore its photocatalytic properties. 30 wt% CoAl-LDH/70 wt% Cv-CN (CCN-2) exhibited the optimal photocatalytic degradation performance after 120 min of light exposure, with a degradation efficiency of 93.1 %. Fukui function calculations, in conjunction with LC-MS/MS analysis, were employed to explore potential degradation pathways during the photocatalytic degradation of tetracycline. The photocatalytic performance of CoAl-LDH/Cv-CN heterojunction was further analyzed by photocatalytic hydrogen production experiments, and after five hours, the hydrogen production rate of CCN-2 was 2515 µmol/g (Cv-CN: 1554 µmol/g, CoAl-LDH: hardly produced any hydrogen). According to the experimental results and data analysis, an effective charge-carrier separation and transfer pathway is established through the interfacial engineering between CoAl-LDH and Cv-CN forming the heterojunction at the interface of CoAl-LDH and Cv-CN. The heterojunction structure formed by interfacial engineering between CoAl-LDH and Cv-CN enables effective photocatalytic removal of antibiotics and hydrogen production providing new insights into the treatment of aqueous environments and clean energy production.

Digital application for drug product potency target evaluation in biopharmaceutical manufacturing.

Biopharmaceutical manufacturing entails a series of highly regulated steps. The manufacturing of safe and efficacious drug product (DP) requires testing of critical quality attributes (CQAs) against specification limits. DP potency concentration, which measures the dosage strength of a particular DP, is a CQA of great interest. In order to minimize the DP potency out-of-specification (OOS) risk, sterile fill finish (SFF) process adjustments may be needed. Varying the potency targets can be one such process adjustment. To facilitate such evaluation, data acquisition and statistical calculations are required. Regularly conducting the OOS risk assessment manually using commercial statistical software can be tedious, error-prone, and impractical, especially when several alternate potency targets are under consideration. In this work, the development of a novel framework for OOS risk assessment and deployment of cloud-based statistical software application to facilitate the risk assessment are presented. This application is intended to streamline the assessment of alternate potency targets for DP in biologics manufacturing. The major aspects of this potency targeting application development are presented in detail. Specifically, data sources, pipeline, application architecture, back-end and front-end development as well as application verification are discussed. Finally, several use cases are presented to highlight the application's utility in biologics manufacturing.

Islanding Detection and Power Quality Diagnosis of Wind Power Integrated Microgrid with Reduced Feature Trained Novel Optimized Random Decision Forest

Distributed generations (DGs) have been increasingly addressing the ongoing power deficit in the electricity market. However, a significant concern in DG-integrated microgrids is the detection of accidental islanding. To tackle this issue, this article proposes a cost-friendly, novel data-driven passive islanding detection scheme named EEMD-HOBRC, combining noise-assisted ensemble empirical mode decomposition (EEMD) and a hybrid optimization-based random forest classifier (HOBRFC). The detection scheme employs a diverse set of features extracted from both raw and EEMD decomposed signals. Essential features are selected using the binary grey wolf optimizer (BGWO) to reduce computational burden. To further improve classification accuracy, the parameters of the random forest classifier are optimized through a hybrid particle swarm and reformed grey wolf optimization (PSRGWO) technique with Cohen’s kappa index as the cost function. The proposed technique is rigorously validated in two different multi-DG environments, encompassing islanding and various nonislanding events. The results demonstrate the effectiveness of the approach in terms of enhanced accuracy, detection time, and performance under both noisy and noise-free conditions. The accuracy of detection under ideal and high noise scenarios is found to be 99.88% and 99.2%, respectively, with maximum detection time of 34.27 ms. Comparative analysis with other algorithms also supports the superiority of the proposed technique. Finally, the method is successfully applied to shrink the nondetection zone (NDZ) with minimal power mismatch, further enhancing its utility in practical applications.

Usability Study of the Mommy-Be App: Exploring the Experience of Breastfeeding Mothers in Eastern Indonesia

Objective: The rise of mobile health (mHealth) apps has brought attention to their potential in supporting breastfeeding mothers and preventing postpartum depression (PPD). This study aims to evaluate the usability of Mommy-Be, a mobile phone app designed to support breastfeeding women and help them to acknowledge of their mental health and breastfeeding efficacy during lactation period. Theoretical Framework: This study uses Usability theory to analyze the use of mHealth applications that proposed by Nielsen model. Method: This study combines quantitative and qualitative methods, that asses Mommy-Be app's usability among breastfeeding mothers using the Mobile Application Usability Questionnaire (MAUQ) and conducted in-depth interviews with a subset of participants. The study included 50 breastfeeding mothers in Makassar, Indonesia, who were primarily between the ages of 19 and 42 and had diverse educational and employment backgrounds. Four weeks after using the Mommy-Be app, revealed a generally positive impression of the application. Result: Based on MAUQ three dimensions, ease of use, interface satisfaction, usefulness, this study has been determined that the utilization of a Mommy-Be application is both acceptable and feasible as a mobile health (mHealth) solution for breastfeeding mothers. The mothers experience revealed diverse user impressions of the Mommy-Be application. Participants generally found it easy to use, with a favorable interface preference. Participants expressed various benefits of using Mommy-Be, including increased awareness of breastfeeding activities, assistance in meeting nutritional needs, and early detection of postpartum depressive disorders. Recommendations: To enhance the application's utility, participants suggested improvements, such as data export capabilities, better module integration, consideration of the target audience's resources regarding internet access and the inclusion of educational content, such as the provision of interconnection with multiple lactation counsellors.

Seminar Dan Pelatihan Peningkatan Pembukuan Dan Upaya Pencegahan Fraud Berbasis Digital Bagi Pelaku UMKM di Lembang Ullin

Community service is a tangible manifestation of a spirit of caring for others. In the context of special needs education, the State Special School in Banjarbaru City faces several challenges, especially in the assessment process of special needs children. Limitations in human resources in terms of teaching staff and technology, as well as conventional assessment methods, are the main obstacles. The solution came in the form of the Special Needs Children Assessment Application called APBAKUS in 2018. Community service through training and socialization of APBAKUS usage in 2019 encouraged the application's utilization. The results of the community service were highly positive, evident in increased efficiency in assessment timing, more coordinated data management, and the improved capabilities of teachers in overcoming obstacles. The APBAKUS application played a crucial role in enhancing the quality of educational services at the State Special School in Banjarbaru City, enabling teachers to provide better services tailored to the needs of special needs children. Thus, community service reflects the spirit of assisting and improving the quality of education for children who require special attention within the community.

Effect of synthesis conditions on the porous texture of activated carbons obtained from Tara Rubber by FeCl3 activation

This paper presents the results of an unique analysis of the influence of the mass ratio of activator FeCl3 to precursor and the temperature of the activation process on the formation of the porous structure of activated carbons obtained from Tara Rubber by FeCl3 activation. The study used the new numerical clustering based adsorption analysis method and the quenched solid density functional theory, taking into account, among other things, the heterogeneity of the analysed surface which is a new approach rarely used in the analysis of the porous structure of adsorbents. On the basis of the calculation results, it was concluded that the activated carbon with the most developed porous texture was obtained at a mass ratio (FeCl3:Tara Rubber) of 2, at an activation process temperature of 800 °C. This activated carbon is also characterised by the lowest degree of surface heterogeneity and at the same time, however, the widest range of micropores compared to activated carbons obtained at other mass ratios. The analyses carried out further demonstrated the valuable and complementary information obtained from the structure analysis methods and their high utility in practical applications, especially in the development of new industrial technologies for the production of adsorbents and the selection of optimal conditions for their production.

Feasibility and acceptability of a dengue self-monitoring system to reduce treatment delay in Malaysia: A single-centre pilot randomised controlled trial.

Most dengue cases are managed in an outpatient setting, where patients are advised to return to the clinic daily for monitoring. Some patients can develop severe dengue at home and fail to recognise the deterioration. An application called DengueAid was designed as a self-monitoring tool for patients to reduce delay in seeking timely treatment. This study aimed to assess the feasibility of conducting a randomised controlled trial to determine the effectiveness of the DengueAid application. Dengue patients were recruited from a public health clinic in Malaysia and randomised to either use the DengueAid application plus standard care for dengue or receive only the standard care. The outcomes evaluated were the (1) feasibility of recruitment, data collection and follow-up procedures; (2) preliminary clinical outcome measures; and (3) acceptability of DengueAid. Qualitative interviews were conducted for participants in the intervention arm to assess the acceptability of DengueAid. Thirty-seven patients were recruited with 97% (n = 36) retention rates. The recruitment rate was low (63% refusal rate, n = 62/99) with difficulty in data collection and follow-up due to the variable interval of care for dengue in an outpatient setting. DengueAid application was acceptable to the participants, but preliminary clinical outcomes and qualitative data suggested limited utility of the application. Unwell conditions of patients and limited access to healthcare are important factors impacting the application's utility. The feasibility trial uncovered issues with recruitment, data collection and follow-up processes. Further research and modification to the application are needed to improve its utility and usability.

Challenges in Acceptance of Smartphone-Based Assistive Technologies: Extending the UTAUT Model for People With Visual Impairments

Introduction: Despite the plethora of sensor-based assistive technology solutions, there is still no widespread acceptance and adoption by people who are blind or have low vision (i.e., visually impaired). Many reasons prevent reducing abandonment levels with a prominent one being a lack of focus on the dimension of training, which, from our standpoint, is integral to the acceptance of assistive technologies. To prove the importance of training, we extend and validate a new version of the Unified Theory of Acceptance and Use of Technology (UTAUT) model incorporating training as a factor. Methods: Closed- and open-ended questionnaires were given online and offline to 231 participants with visual impairments after conducting training sessions with an application for outdoor navigation by people with visual impairments developed by our research team. To assess the UTAUT extension exploratory factor analysis, confirmatory factor analysis, and structural equation model were employed to explore the relationships between the factors. A usability and user experience qualitative analysis supplemented the previous. Results: We uncovered that no factor besides performance expectancy (standardized regression weight = 0.264, p &lt; .001) and training (standardized regression weight = 0.538, p &lt; .001) significantly predict behavioral intention. Furthermore, the analysis demonstrated a significant interaction ( p &lt; .007) strengthening the positive relationship between training and behavioral intention (standardized regression weight = 0.142). The qualitative analysis showed an overall positive evaluation highlighting the application's usefulness and dependability. Discussion: An application's adoption increases if individuals who are visually impaired are properly trained and acquainted with the features in real-life scenarios and recognize the application's utility for their daily lives. Implications for Practitioners: Training plays an important role in technology acceptance. It can be leveraged to make solutions more appealing to people who are visually impaired.

Experimental study on the performance enhancement of PV/T by adding graphene oxide in paraffin phase change material emulsions

Traditional water-based PV/T systems have low heat storage density, high PV backsheet temperatures, and low energy utilization in practical applications. In this work, nanoparticles were applied to improve thermal conductivity and simultaneously emulsions were added to enhance energy storage density of the conventional heat transfer media. Furthermore, the synergistic effect of nanocomposite Phase Change Material Emulsions (PCME) as the heat transfer medium on the thermoelectric efficiency of PV/T was studied in a real system. Specifically, the water-based 30 % paraffin emulsions with graphene oxide (GO) concentration of 0.01, 0.02 and 0.03 wt% were prepared by ultrasonic stirring and their thermophysical properties were characterized. The results show that the 30 wt% paraffin emulsion with addition of 0.02 wt% GO has the phase change temperature of 35 °C, latent heat of 42.93 J/g, thermal conductivity of 0.505 W/(m·K) and viscosity coefficient of 0.91. It shows the thermal efficiency of the paraffin/GO emulsion increased by 92.28 %, the electrical efficiency increased by 8.87 %, the comprehensive efficiency increased by 45.75 %, and 15.8 % increase in heat collection for the heat exchange tank in comparison with the water. It is concluded application of PCME would improves the thermoelectric performance of the system than traditional water-based PV/T systems.

Application of mixed reality and artificial intelligence to assist medical students in learning injection technique

Introduction: The usage of immersive technology has advanced in a number of areas of life because of the development of technology that keeps pace with the times. Another immersive technology that combines VR and AR is mixed reality (MR), which enables us to interact with 3-dimensional objects in the real world. Since MR technology gives a more nuanced experience, the market is highly promising. This study aims to evaluate the application of mixed reality and artificial intelligence to assist medical students in learning injection technique. Methods: This type of research is analytic with a quantitative and qualitative approach to prove the purpose of the research. This research involved 40 students. Due to the creative nature of immersive technology, it must be combined with other technologies to produce an even more complicated and engaging experience. In order to enhance the quality of the user experience, we will merge MR immersive technology with AI in this research for medical educational field. The integration of these two technologies via an application that can be launched on a Hololens 2 and Magic Leap 1 device and can identify person in a laboratory to support in student learning. Results: For instance, students can utilize artificial intelligence (AI) to learn the names of objects in the lab and do simulation about injection technique. The study 's outcomes are presented in software testing (FPS, CPU, GPU, and load scene) an in the form of user testing utilizing the PIECES Framework (Performance, Information and Data, Economy, Control and Security, Efficiency, and Service), which evaluates the application's utility or significance as well as the satisfaction of its users. Conclusion: The system was able to develop a combining application of artificial intelligence and mixed reality for detecting objects in laboratories to assist learning students, according to the study's conclusions.

Pelatihan Dan Sosialisasi Pemanfaatan APBAKUS 2 Di Sekolah Luar Biasa Negeri Kota Banjarbaru

Community service is a tangible manifestation of a spirit of caring for others. In the context of special needs education, the State Special School in Banjarbaru City faces several challenges, especially in the assessment process of special needs children. Limitations in human resources in terms of teaching staff and technology, as well as conventional assessment methods, are the main obstacles. The solution came in the form of the Special Needs Children Assessment Application called APBAKUS in 2018. Community service through training and socialization of APBAKUS usage in 2019 encouraged the application's utilization. The results of the community service were highly positive, evident in increased efficiency in assessment timing, more coordinated data management, and the improved capabilities of teachers in overcoming obstacles. The APBAKUS application played a crucial role in enhancing the quality of educational services at the State Special School in Banjarbaru City, enabling teachers to provide better services tailored to the needs of special needs children. Thus, community service reflects the spirit of assisting and improving the quality of education for children who require special attention within the community.