End Users Research Articles

Improving preparation in the emergency trauma room: the development and impact of real-time data transfer and dashboard visualization system.

This study examines, with clinical end users, the features of a visualization system in transmitting real-time patient data from the ambulance to the emergency trauma room (ETR) to determine if the real-time data provides the basis for more informed and timely interventions in the ETR before and after patient arrival. We conducted a qualitative in-depth interview study with 32 physicians in six German and Swiss hospitals. A visualization system was developed as prototype to display the transfer of patient data, and it serves as a basis for evaluation by the participating physicians. The prototype demonstrated the potential benefits of improving workflow within the ETR by providing critical patient information in real-time. Physicians highlighted the importance of features such as the ABCDE scheme and vital signs that directly impact patient care. Configurable and mobile versions of the prototype were suggested to meet the specific needs of each clinic or specialist, allowing for the transfer of only essential information. The results highlight on the one hand the potential need for adaptable interfaces in medical communication technologies that balance efficiency with minimizing additional workload for emergency medical services and show that the use of pre-notification systems in communication between ambulance and hospital can be supportive. Further research is recommended to assess practical application and support in clinical practice, including a re-evaluation of the enhanced prototype by professionals.

How to (or how not to) implement crowdsourcing for the development of health interventions: lessons learned from four African countries.

Crowdsourcing strategies are useful in the development of public health interventions. Crowdsourcing engages end users in a co-creation process through challenge contests, designathons or online collaborations. Drawing on our experience of crowdsourcing in four African countries, we provide guidance on designing crowdsourcing strategies across seven steps: deciding on the type of crowdsourcing strategy, convening a steering committee, developing the content of the call for ideas, promotion, evaluation, recognizing finalists and sharing back ideas or implementing the solutions.

Mathematical Modeling and Comparative Analysis of Noise and Vibration Characteristics of CI Engine Fueled with Biodiesel

As an alternative to fossil fuels, renewable energy has the potential to replace diesel in CI engines, and therefore biodiesels such as nahar, jatropha, karanja, etc. are being used as a blend with diesel in CI engines. Since biodiesel is a sustainable fuel, numerous researchers have evaluated and contrasted its performance attributes with those of diesel. The end user’s comfort and level of fatigue following the usage of biodiesel blended with diesel, however, is an interesting area that requires further investigation. The current study aims to investigate the noise and vibration characteristics of unmodified and constant-speed CI engines powered by jatropha, nahar, or karanja biodiesel as a blend with diesel and also developed a mathematical model for noise and vibration responses. The vibration and sound pressure level were recorded using the FFT analyzer Brüel & Kjær Photon+ portable measuring system with RTPro software for different input parameters such as load, density, flash point, and calorific value at different levels for diesel D100 and biodiesel blends. Mathematical non-linear model was developed to predict the relationship between fuel properties and engine noise-vibration characteristics because the R square and adj. R square values of model is found to be close to each other. However, higher adj. R square value and p-value within 0.05 are the good criteria for selection of model.

Omnidirectional soft pneumatic actuators: a design and optimization framework.

Soft pneumatic actuators (SPAs) play a pivotal role in soft robotics due to their unique characteristics of compliance, flexibility, and adaptability. There are plenty of approaches that examine the modeling parameters of SPAs, aiming to optimize their design and, thus, achieve the most advantageous responses. Current optimization methods applied to SPAs are usually performed individually for each design parameter without considering the simultaneous effect all parameters can have on the output performance. This modeling shortcoming is essential to be addressed since customized SPAs are used in a variety of applications, each with different output requirements. This study provides a generalized design optimization framework for modeling the SPA performance for their motion profiles, the produced strain energy while being deformed, and their stiffness characteristics. Utilizing experimentally validated finite element methods, all geometrical and material parameters of the models are investigated in response surface methodology optimization using the central composite design approach. The results showcase the entire design space of omnidirectional SPAs, along with their output performance, providing guidelines to the end user for design optimization. The offering of this modeling process for SPAs can be adapted to the demands of any potential application and ensure the best performance with respect to the required output responses.

Developing an ensemble machine learning study: Insights from a multi-center proof-of-concept study.

To address the numerous unmeet clinical needs, in recent years several Machine Learning models applied to medical images and clinical data have been introduced and developed. Even when they achieve encouraging results, they lack evolutionary progression, thus perpetuating their status as autonomous entities. We postulated that different algorithms which have been proposed in the literature to address the same diagnostic task, can be aggregated to enhance classification performance. We suggested a proof of concept to define an ensemble approach useful for integrating different algorithms proposed to solve the same clinical task. The proposed approach was developed starting from a public database consisting of radiomic features extracted from CT images relating to 535 patients suffering from lung cancer. Seven algorithms were trained independently by participants in the AI4MP working group on Artificial Intelligence of the Italian Association of Physics in Medicine to discriminate metastatic from non-metastatic patients. The classification scores generated by these algorithms are used to train SVM classifier. The Explainable Artificial Intelligence approach is applied to the final model. The ensemble model was validated following an 80-20 hold-out and leave-one-out scheme on the training set. Compared to individual algorithms, a more accurate result was achieved. On the independent test the ensemble model achieved an accuracy of 0.78, a F1-score of 0.57 and a log-loss of 0.49. Shapley values representing the contribution of each algorithm to the final classification result of the ensemble model were calculated. This information represents an added value for the end user useful for evaluating the appropriateness of the classification result on a particular case. It also allows us to evaluate on a global level which methodological approaches of the individual algorithms are likely to have the most impact. Our proposal represents an innovative approach useful for integrating different algorithms that populate the literature and which lays the foundations for future evaluations in broader application scenarios.

Improving transparency and quality assurance: Operationalising semi-automated data provenance tracking in a Trusted Research Environment

We present a prototype solution for improving transparency and quality assurance of the data linkage process through a data provenance dashboard designed to assist data analysts, researchers and information governance teams in authenticating and auditing data workflows within a trusted research environment (TRE). Building on prior research (Scheliga, et al., 2022), this work describes our first operationalised prototype tested in a real-world setting. The prototype development involved four stages: (1) Co-design of interfaces with end users for provenance data collection and visualisation, producing a low-fidelity design; (2) Extension and refinement of the Safe Haven Provenance (SHP) ontology (https://tre-provenance.github.io/SHP-ontology/releases/v0.2/index-en.html); (3) Design and implementation of mechanisms for semi-automated collection of data linkage provenance using the SHP ontology; (4) Implementation and user evaluation of the dashboard. A participatory design process with data analysts, researchers and information governance teams resulted in a low-fidelity prototype and was validated via public consultations to ensure it met public trust. The resulting prototype dashboard (https://tre-provenance.github.io/) was built as an offline desktop app to match the deployment TRE requirements. The interactive dashboard displays the data linkage information extracted from a knowledge graph described using the SHP ontology (e.g., modifications of datasets, data release) and results of rule-based validation checks (e.g., checking extracted data against researchers' specification). User evaluations confirmed the dashboard would contribute to better quality of data linkage. This project demonstrates the next stage in advancing transparency and quality assurance within TREs by semi-automating and systematising data tracking from ingress to egress in a single tool.

Designing a Data Dashboard for Health Departments and Overdose Fatality Review Teams

IntroductionOverdose Fatality Review (OFR) teams within health departments rely on data from multiple isolated sources to study the opioid crisis. Recently, we linked electronic health record data with state agency data to form a regional Substance Misuse Data Commons (SMDC) using privacy-preserving record linkage. Our goal in this study was to use human factors design principles to design a data dashboard for OFR teams using the linked datasets that will overcome current barriers within OFR workflows. MethodsWe utilized NASA task load surveys, semi-structured interviews, and design sessions with end users to identify data needs for an optimal dashboard design. We assessed current workloads, data collection processes, and desired future state. We subsequently performed iterative design sessions for the generation and evaluation of low-fidelity prototypes. To overcome issues with privacy and security, we used synthetic data in a cloud-based platform to represent the SMDC for simulation. ResultsEleven OFR organizers participated. Pre-dashboard surveys on existing workflow showed high mental workload associated with data aggregation and case review, identifying a need for more accessible, comprehensive data. In our low-fidelity dashboard demo with synthetic data, iterative design adjustments were made in data visualization, storyline organizations, and theme-based data aggregation across pre-hospital and hospital data. ConclusionsWe refined the data dashboard prototype into a high-fidelity version, set for further usability and human factors evaluation. We addressed privacy and security concerns through synthetic data use while the real-world data is maintained in a HIPAA-secure Azure cloud environment with access for approved users.

Energy performance certificate calculation methodologies across Europe and accommodating new performance indicators

Energy Performance Certificates (EPC) are used across Europe to communicate the energy performance of buildings to a range of different end users. However, as new approaches are introduced and guided at the European level via the Energy Performance Buildings Directive (EPBD), the ability of assessment methodologies and assessors to accommodate these new forms is likely to differ due to the significantly different frameworks in each country. The Horizon-funded crossCert project investigates this by identifying how EPC methodologies differ across countries, highlighting the implications of these differences on the performance gap and what that means for future innovations. Results indicate that methodologies vary considerably regarding general approaches, from highly standardised to highly tailored and assessor qualifications. This paper will look at such differences and investigate how these differences can affect future efforts towards improving EPCs.

Installation of Clean Water Piping for Resident on Jl. Arjuna, RW 08 and 09, East Labuh Baru, Pekanbaru

Water is a crucial resource for sustaining life; however, access to it through the Regional Drinking Water Company (Indonesian: Perusahaan Daerah Air Minum [PDAM]) remains limited in certain communities. As a result, residents frequently depend on groundwater sourced through independent pumping by households, places of worship, public facilities, private and government offices, and others. An assessment of the buildings on Jl. Arjuna RW 08 and 09, East Labuh Baru District, Pekanbaru, indicates a significant lack of adequate clean water installation systems, highlighting a need for targeted community service efforts. This initiative aims to rectify these deficiencies by drilling wells to establish reliable sources of clean water and installing a comprehensive clean water piping system to ensure effective distribution from the source to the end users, thus aligning with Indonesian National Standards (SNI). The project involves faculty members as part of their commitment to the tri-dharma of higher education, offering both a practical learning opportunity for students and a valuable service to the community.

Software System Architecture for Estimating Software Development Time

The article is devoted to the issues of estimating the duration of software development, the solution of which can significantly improve the efficiency of software projects. The relevance of the topic is conditioned by the rapid development of software development methodologies, on which the existing algorithms of such estimation depend, and, as a consequence, by the rapid obsolescence of approaches to solving this problem. A systematic analysis of the main algorithms for estimating software development duration is carried out. The classification of such algorithms is presented. The algorithm of software development duration estimation and the idea of the system implementing it, which will allow end users to automate this process, are proposed. The approaches to implementation of algorithms of retrospective (historical) estimation, PERT, expert estimation are considered. The prospectivity of researches in the field of implementation of methods of expert evaluation using neural networks is shown. The architecture of the proposed system is described. A prototype of the system implementing the method of retrospective evaluation based on the evaluation of the speed of the development team is developed.

Calibration-free and ready-to-use wearable electroanalytical reporting system (r-WEAR) for long-term remote monitoring of electrolytes markers

A major bottleneck in the development of wearable ion-selective sensors is the inherent conditioning and calibration procedures at the user's end due to the signal's instability and non-uniformity. To address this challenge, we developed a strategy that integrates three interdependent materials and device engineering approaches to realize a Ready-to-use Wearable ElectroAnalytical Reporting system (r-WEAR) for reliable electrolytes monitoring. The strategy collectively utilized (1) finely-configured diffusion-limiting polymers to stabilize the electromotive force in the electrodes, (2) a uniform electrical induction in electrochemical cells to normalize the open-circuit potential (OCP), and (3) an electrical shunt to maintain the OCP across the entire sensor in the r-WEAR. The approaches jointly enable fabrication of homogeneously stable and uniform ion-selective sensors, eliminating common conditioning and calibration practices. As a result, the r-WEAR demonstrated a signal's variation down to ±1.99 mV with a signal drift of 0.5 % per hour (0.12 mV h−1) during a 12-h continuous measurement of 10 sensors and a signal drift as low as 13.3 μV h−1 during storage. On-body evaluations of the r-WEAR for four days without conditioning and re-/calibration further validated the sensor's performance in realistic settings, indicating its remarkable potential for practical usage in a user operation-free manner in wearable healthcare applications.

Brainchop: Providing an Edge Ecosystem for Deployment of Neuroimaging Artificial Intelligence Models.

Deep learning has proven highly effective in various medical imaging scenarios, yet the lack of an efficient distribution platform hinders developers from sharing models with end-users. Here, we describe brainchop, a fully functional web application that allows users to apply deep learning models developed with Python to local neuroimaging data from within their browser. While training artificial intelligence models is computationally expensive, applying existing models to neuroimaging data can be very fast; brainchop harnesses the end user's graphics card such that brain extraction, tissue segmentation, and regional parcellation require only seconds and avoids privacy issues that impact cloud-based solutions. The integrated visualization allows users to validate the inferences, and includes tools to annotate and edit the resulting segmentations. Our pure JavaScript implementation includes optimized helper functions for conforming volumes and filtering connected components with minimal dependencies. Brainchop provides a simple mechanism for distributing models for additional image processing tasks, including registration and identification of abnormal tissue, including tumors, lesions and hyperintensities. We discuss considerations for other AI model developers to leverage this open-source resource.

Conceptual Design Process of a Missile Model and Production Using Additive Manufacturing Method

This study focuses on air-to-ground missile systems, which are widely used in Turkey and around the world and are becoming increasingly important. The development of missile systems takes into account various requirements defined by the end user. It is important to identify a system and its subcomponents that fully meet the requirements. This study analyzes an air-to-ground missile system and its main subcomponents identified through the conceptual design method based on the systematic design approach proposed by Pahl and Beitz. The aim is to determine the feasibility of obtaining an optimal solution that meets the requirements set by the conceptual design method. The missile design’s optimal solution was modeled using SolidWorks software. A three-dimensional (3D) printer with FDM production technology was used to produce a prototype of the computer-modeled design. ABS and ABS-plastic blend filaments were preferred due to their material properties in the FDM production process. During the printing stage, the filament and output settings of the model were determined using the 3D printer’s interface program. The filaments were then extruded through a nozzle, following the cross-sectional geometry of the part. The resulting model was printed in pieces and assembled with a tolerance of 0.1mm. This process resulted in a 3D model of the missile, which was created to represent the system structure in different colours. The study demonstrates that the conceptual design method can be used to develop innovative and meaningful missile models.

Modelling user notification scenarios in privacy policies

The processing of personal data gives a rise to many privacy concerns, and one of them is to ensure the transparency of data processing to end users. Usually this information is communicated to them using privacy policies. In this paper, the problem of user notification in case of data breaches and policy changes is addressed, besides an ontology-based approach to model them is proposed. To specify the ontology concepts and properties, the requirements and recommendations for the legislative regulations as well as existing privacy policies are evaluated. A set of SPARQL queries to validate the correctness and completeness of the proposed ontology are developed. The proposed approach is applied to evaluate the privacy policies designed by cloud computing providers and IoT device manufacturers. The results of the analysis show that the transparency of user notification scenarios presented in the privacy policies is still very low, and the companies should reconsider the notification mechanisms and provide more detailed information in privacy policies.

Future Shorelines: A Living Shoreline Site Selection and Design Decision Support Tool that Incorporates Future Conditions Induced by Sea Level Rise

Most living shoreline site selection and design decision support tools are based upon existing environmental conditions. We developed a web-based, geospatial tool called Future Shorelines that integrates high-resolution landscape elevation data and a matrix of locally derived NOAA Interagency Sea Level Rise Scenarios to characterize future conditions of submergence and shoreline translation induced by sea level rise. Once the practitioner selects a location of interest, sea level rise scenario (e.g., high), and target year (e.g., 2050), the tool will generate plan view and cross-sectional informational graphics specific to their choices. This information can then be paired with other menu options, like parcel ownership, to facilitate the planning and construction of nature-based shoreline stabilization solutions that (1) are located where opportunities for horizontal migration are optimized, (2) remain accessible for monitoring and maintenance, and (3) perform as intended over the design life of the installation. The tool’s menu options and the user interface were informed by project partner input solicited during numerous workshops convened over the duration of the 2-year project. This coproduction created a product that was familiar to the end user and therefore increased the likelihood that it would be utilized by them during the planning and design of living shoreline projects. Although developed for use in the Indian River Lagoon, located along the east-central Florida coast, it can be seamlessly replicated for application in other coastal regions of the USA where the requisite data are available.

Applying cognitive walkthrough methodology to improve the usability of an equity-focused implementation strategy

BackgroundOur research team partnered with primary care and quality improvement staff in Federally Qualified Community Health Centers (CHCs) to develop Partnered and Equity Data-Driven Implementation (PEDDI) to promote equitable implementation of evidence-based interventions. The current study used a human-centered design methodology to evaluate the usability of PEDDI and generate redesign solutions to address usability issues in the context of a cancer screening intervention.MethodsWe applied the Cognitive Walkthrough for Implementation Strategies (CWIS), a pragmatic assessment method with steps that include group testing with end users to identify and prioritize usability problems. We conducted three facilitated 60-min CWIS sessions with end users (N = 7) from four CHCs that included scenarios and related tasks for implementing a colorectal cancer (CRC) screening intervention. Participants rated the likelihood of completing each task and identified usability issues and generated ideas for redesign solutions during audio-recorded CWIS sessions. Participants completed a pre-post survey of PEDDI usability. Our research team used consensus coding to synthesize usability problems and redesign solutions from transcribed CWIS sessions.ResultsUsability ratings (scale 0–100: higher scores indicating higher usability) of PEDDI averaged 66.3 (SD = 12.4) prior to the CWIS sessions. Scores averaged 77.8 (SD = 9.1) following the three CWIS sessions improving usability ratings from “marginal acceptability” to “acceptable”. Ten usability problems were identified across four PEDDI tasks, comprised of 2–3 types of usability problems per task. CWIS participants suggested redesign solutions that included making data fields for social determinants of health and key background variables for identifying health equity targets mandatory in the electronic health record and using asynchronous communication tools to elicit ideas from staff for adaptations.ConclusionsUsability ratings indicated PEDDI was in the acceptable range following CWIS sessions. Staff identified usability problems and redesign solutions that provide direction for future improvements in PEDDI. In addition, this study highlights opportunities to use the CWIS methodology to address inequities in the implementation of cancer screening and other clinical innovations in resource-constrained healthcare settings.

A Roadmap to Industry Based Curriculum in Higher Education Through Public-Private Partnership Model

Higher education in any country plays an important role in nation building. Education system has a social agenda to develop its human resource in a better way to meet the requirements of society. Several reforms were introduced to promote quality in higher education and make education accessible to every society. The continuous amendments in education policies are required to meet the present expectations of industry. The traditional approach of rote learning and memory level teaching shall not work out in the modern times where the requirements of industry are changing frequently. There is a need of an hour for the higher institutions to shift their approach from academic based curriculum to industry-based curriculum. Many higher education institutions are struggling to provide quality, affordable education and research to its end users. Thus, a collaborative approach needs to be followed in the form of public-private partnership model for facilitating practical learning in higher institutions and preparing the future budding managers to bridge the gap between skills required to meet industry expectations and the skills they possess. The aim of this paper is to explore about the PPP model for promoting industry-based curriculum in academics. The study is purely secondary in nature followed with exploratory research-design for giving a broader view on implementation of PPP model in higher institutions. The present study provides an integrated process through which the effectiveness and working of PPP model is well-explained.

Availability of Evidence for Predictive Machine Learning Algorithms in Primary Care

The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most (27 [63%]) focused on cardiovascular diseases and diabetes. Most (35 [81%]) were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19% and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45% vs 29%). The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms' quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.

Value of Engagement in Digital Health Technology Research: Evidence Across 6 Unique Cohort Studies.

Wearable digital health technologies and mobile apps (personal digital health technologies [DHTs]) hold great promise for transforming health research and care. However, engagement in personal DHT research is poor. The objective of this paper is to describe how participant engagement techniques and different study designs affect participant adherence, retention, and overall engagement in research involving personal DHTs. Quantitative and qualitative analysis of engagement factors are reported across 6 unique personal DHT research studies that adopted aspects of a participant-centric design. Study populations included (1) frontline health care workers; (2) a conception, pregnant, and postpartum population; (3) individuals with Crohn disease; (4) individuals with pancreatic cancer; (5) individuals with central nervous system tumors; and (6) families with a Li-Fraumeni syndrome affected member. All included studies involved the use of a study smartphone app that collected both daily and intermittent passive and active tasks, as well as using multiple wearable devices including smartwatches, smart rings, and smart scales. All studies included a variety of participant-centric engagement strategies centered on working with participants as co-designers and regular check-in phone calls to provide support over study participation. Overall retention, probability of staying in the study, and median adherence to study activities are reported. The median proportion of participants retained in the study across the 6 studies was 77.2% (IQR 72.6%-88%). The probability of staying in the study stayed above 80% for all studies during the first month of study participation and stayed above 50% for the entire active study period across all studies. Median adherence to study activities varied by study population. Severely ill cancer populations and postpartum mothers showed the lowest adherence to personal DHT research tasks, largely the result of physical, mental, and situational barriers. Except for the cancer and postpartum populations, median adherences for the Oura smart ring, Garmin, and Apple smartwatches were over 80% and 90%, respectively. Median adherence to the scheduled check-in calls was high across all but one cohort (50%, IQR 20%-75%: low-engagement cohort). Median adherence to study-related activities in this low-engagement cohort was lower than in all other included studies. Participant-centric engagement strategies aid in participant retention and maintain good adherence in some populations. Primary barriers to engagement were participant burden (task fatigue and inconvenience), physical, mental, and situational barriers (unable to complete tasks), and low perceived benefit (lack of understanding of the value of personal DHTs). More population-specific tailoring of personal DHT designs is needed so that these new tools can be perceived as personally valuable to the end user.

FedGST: An Efficient Federated Graph Neural Network for Spatio-temporal PoI Recommendation

With the proliferation of sensor networks in urban areas, vast amounts of data from location-based social network platforms are now available, thus enabling the stakeholders to develop location-aware services for the end users. PoI (Point of Interests) recommendation is one of the most trending services. PoI recommendation models are developed by considering geographical information and historical records. More recently, with the demand for achieving PoI recommendations on mobile devices, embedded devices, or Internet of Things (IoT) devices, the challenges posed by the limited computational resources, malicious clients, and data silos, the model performance gets immensely affected. To address the above challenges and achieve efficient PoI recommendations, we propose an efficient federated graph learning-based model for mining complex spatiotemporal features to generate recommendations. We implement a GRU-based encoder-decoder to learn the temporal hidden state embeddings. Simultaneously, a 2-layer graph network is used to understand spatial embedding vectors. We also introduce an efficient contribution evaluation method to speed up the training process and improve the recommendation performance. Experiments on the PoI recommendation task based on real-life check-in data validate the effectiveness of our proposed model, and the results indicate that our recommendation model can achieve competitive results with lower computational costs.