Usability Of Approaches Research Articles

Expression of Oxidative Stress and Inflammatory Indicators for Coronary Artery Disease in Kawasaki Disease.

The paper was to investigate the clinical relevance of oxidative stress (OS) and inflammation-associated targets in coronary artery lesions (CALs) associated with Kawasaki disease (KD). The clinical data from 455 sufferers diagnosed with KD between February 2021 and June 2023 were gathered and divided into two groups: CAL and NCAL. The regression analysis was conducted to search for independent covariates for CALs related to OS and inflammation. The predictive nomogram was structured according to these risk factors. The properties of the model were estimated using calibration and receiver operating characteristic curves. The levels of CRP, IL-6, PLT count, ESR, ox-HDL, MDA, and PLR were more elevated in CAL patients with KD; interestingly, HDL and superoxide dismutase (SOD) were low in the CAL group. Ascension of CRP, IL-6, ESR, ox-HDL, MDA, and PLR, and diminution of HDL and SOD were considered independent risk factors. The nomogram constructed using these factors demonstrated a satisfactory calibration degree and discriminatory power, with an area under the curve of 0.812. In the verification set, the area under the curve was found to be 0.799. The model was established according to 8 OS and inflammation-associated risk factors bound up with CALs in KD sufferers. It may be a usable approach for early diagnosis of CALs in KD.

Using group level factor models to resolve high dimensionality in model-based sampling.

Joint modeling of decisions and neural activation poses the potential to provide significant advances in linking brain and behavior. However, methods of joint modeling have been limited by difficulties in estimation, often due to high dimensionality and simultaneous estimation challenges. In the current article, we propose a method of model estimation that draws on state-of-the-art Bayesian hierarchical modeling techniques and uses factor analysis as a means of dimensionality reduction and inference at the group level. This hierarchical factor approach can adopt any model for the individual and distill the relationships of its parameters across individuals through a factor structure. We demonstrate the significant dimensionality reduction gained by factor analysis and good parameter recovery, and illustrate a variety of factor loading constraints that can be used for different purposes and research questions, as well as three applications of the method to previously analyzed data. We conclude that this method provides a flexible and usable approach with interpretable outcomes that are primarily data-driven, in contrast to the largely hypothesis-driven methods often used in joint modeling. Although we focus on joint modeling methods, this model-based estimation approach could be used for any high dimensional modeling problem. We provide open-source code and accompanying tutorial documentation to make the method accessible to any researchers. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Exploring Students’ Hands-On Performance, Attitudes, and Usability with Arduino Modular Boards

Utilizing Arduino development boards for learning microcontroller circuits is a prevalent practice across various educational levels. Nevertheless, the literature offers limited insights into the impact of these boards on student performance and attitudes. Therefore, this paper aims to investigate the performance of 58 university students in learning microcontroller circuits with modular boards designed for Arduino through a series of 4 exercises. Specifically, students’ performance is assessed through pre-tests and post-tests, in three learning units: (a) microcontroller, (b) coding, and (c) circuit. Additionally, the study captures students’ attitudes and measures their perceived usability of modular boards. For this purpose, the students completed a specially designed attitude questionnaire and the system usability scale (SUS) questionnaire. Statistical analysis is conducted using t-tests, ANOVA, and ANCOVA, along with bootstrapping. The findings reveal statistically significant differences between pre-tests and post-tests in all cases. Among the three learning units, the use of modular boards appears to have the most significant impact on coding. Based on students’ responses, the SUS results indicate that modular boards appear to be a quite usable approach for teaching microcontrollers. Finally, students generally express positive attitudes toward modular boards.

Analysis of the Level of Satisfaction with the Use of Computer Assisted Test at SMAN 1 Parang Magetan

The use of technology in education sector provides many conveniences in carrying out learning activities. One use of technology in the education sector can be used by teaching staff to carry out evaluations after carrying out a series of learning activities. The technology that can be used can be in any form, one of which is a system that is built to facilitate the learning process from start to finish. One system that can be used is the systemComputer Assisted Test (CAT). CAT is a system that uses computers as the main medium. In the CAT system, practice questions can be input which will be filled in by students later. This CAT system is used by students to work on practice questions. The system that has been used needs to be evaluated to determine its advantages and disadvantages. One method that can be used to analyze a system is the usability approach User Satisfaction Quesionnaire (UEQ). This approach uses user experience as the main aspect in system assessment and there are 6 variables assessed, namely Attractiveness (Daya Tarik), Efficiency (Efisiensi), Clarity (Tingkat Kejelasan), Dependability (Ketepatan), Stimulation (Stimulasi), and Novelty (Kebaruan). This research uses a UEQ questionnaire which will be filled in by 88 students and 12 teachers who act as research samples after working on practice questions through the CAT system. The completed questionnaire was then analyzed and it was discovered that for the Attractiveness, Efficiency, Clarity and Stimulation variables received the "Very Good" criteria, the Novelty variable "Good", and the Dependability variable "Below Average".

How to Model Human–Robot Collaborative Logistics Systems: Systematic Literature Review and Future Perspectives

Thanks to rapid technological developments in robotics, various automation technologies have been introduced into different logistics systems. A human–robot collaborative logistics system can contain different technologies. Until now, most studies have focused on technologies that could only partially automate the logistics process. In contrast, some market-ready products exist with which the entire logistics process could be automated. An example is the hybrid order picking system, which utilizes autonomous mobile robots to conduct picking and transporting tasks and can be integrated into manual warehouses. In this case, human workers and robots can be modeled as heterogeneous agents with strengths and weaknesses. To date, the issue of how to model these logistics systems has remained largely unaddressed. Inspired by this system, this work intends to contribute to the discussion of possible (analytical) modeling approaches to leverage the strengths of both humans and robots to achieve better outcomes. To this end, a systematic literature review was conducted to find usable approaches in adjacent disciplines. We identified modelling approaches in the field of last-mile delivery, in-house transportation, assembly, and robotics, which considered a (human-robot) heterogenous team in the task allocation. Efforts are then made to construct a framework for possible design variables for such logistics systems to offer promising insights and perspectives for future research.

Design of an Iot Based Automatic Lawn Vacuum & Leaf Bag Using Usability and Work Posture Method

Smart Garden is a system design created to make work in plantations easier. Currently, most Indonesians use sling type lawn mowers because they are cheap but can causing noise and air pollution. It can also cause CTDS in users due to bad posture while using the tool. The researchers innovated an IoT-based automatic cutting machine. Where in the machine application, the machine can be moved using a smartphone connected using bluetooth. Which consists of two options, namely machine and vacuum. The REBA method are used to analyzing ergonomics for all parts of the body and a usability method which will determine the extent to which the product can achieve effectiveness, efficiency and comfort. This data collection was carried out by distributing the SUS questionnaire. The REBA results showed that the average body posture at moderate risk had a score of 7.8 and 9 which required further analysis of the bent posture even though it was still classified as moderate. Meanwhile, the results of the usability approach use a questionnaire as a reference for processing data. From this data, users can accept the presence of the Control Smart System Application and are quite satisfied with the interface used.

Segmentation of Dynamic Total-Body [18F]-FDG PET Images Using Unsupervised Clustering.

Clustering time activity curves of PET images have been used to separate clinically relevant areas of the brain or tumours. However, PET image segmentation in multiorgan level is much less studied due to the available total-body data being limited to animal studies. Now, the new PET scanners providing the opportunity to acquire total-body PET scans also from humans are becoming more common, which opens plenty of new clinically interesting opportunities. Therefore, organ-level segmentation of PET images has important applications, yet it lacks sufficient research. In this proof of concept study, we evaluate if the previously used segmentation approaches are suitable for segmenting dynamic human total-body PET images in organ level. Our focus is on general-purpose unsupervised methods that are independent of external data and can be used for all tracers, organisms, and health conditions. Additional anatomical image modalities, such as CT or MRI, are not used, but the segmentation is done purely based on the dynamic PET images. The tested methods are commonly used building blocks of the more sophisticated methods rather than final methods as such, and our goal is to evaluate if these basic tools are suited for the arising human total-body PET image segmentation. First, we excluded methods that were computationally too demanding for the large datasets from human total-body PET scanners. These criteria filtered out most of the commonly used approaches, leaving only two clustering methods, k-means and Gaussian mixture model (GMM), for further analyses. We combined k-means with two different preprocessing approaches, namely, principal component analysis (PCA) and independent component analysis (ICA). Then, we selected a suitable number of clusters using 10 images. Finally, we tested how well the usable approaches segment the remaining PET images in organ level, highlight the best approaches together with their limitations, and discuss how further research could tackle the observed shortcomings. In this study, we utilised 40 total-body [18F] fluorodeoxyglucose PET images of rats to mimic the coming large human PET images and a few actual human total-body images to ensure that our conclusions from the rat data generalise to the human data. Our results show that ICA combined with k-means has weaker performance than the other two computationally usable approaches and that certain organs are easier to segment than others. While GMM performed sufficiently, it was by far the slowest one among the tested approaches, making k-means combined with PCA the most promising candidate for further development. However, even with the best methods, the mean Jaccard index was slightly below 0.5 for the easiest tested organ and below 0.2 for the most challenging organ. Thus, we conclude that there is a lack of accurate and computationally light general-purpose segmentation method that can analyse dynamic total-body PET images.

Evaluating the User Interface and Usability Approaches for E-Learning Systems

E-learning offers an experience that is not constrained by time or geography. Owing to the advancements in technology and accessible computing, users have several ways to interact with e-learning programs. Therefore, usability approaches are crucial for the success of an e-learning application or a website. This study investigates various user-interface usability evaluation methods (UEM) and distribution of e-learning web-based applications, such as Moodle, Blackboard, Learning Management System (LMS), Zoom, Google Classroom, Facebook, and other online programs that exist for online education. To evaluate the usability features of online educational apps and websites, including their effectiveness and usability for students, a survey was conducted to collect responses on online education.

A novel scoring approach for the Wolf Motor Function Test in stroke survivors using motion-sensing technology and machine learning: A preliminary study

Background and objectiveHuman-administered clinical scales, such as the Functional Ability Scale of the Wolf Motor Function Test (WMFT-FAS), are widely utilized to evaluate upper-limb motor function in stroke survivors. However, these scales are generally subjective and labor-intensive. To end this, we proposed a novel scoring approach for the motor function assessment. MethodsThe proposed novel scoring approach mainly contained one Microsoft Kinect v2, one customized motion tracking system, and one customized intelligent scoring system. Specifically, the Kinect v2 was used to capture stroke survivors’ functional movements, the motion tracking system was developed for recording the gathered movement data, and the intelligent scoring system (kernel: feed-forward neural network, FFNN) was developed to evaluate movement quality and provide corresponding WMFT-FAS scores. Several methods have been applied to enhance the approach's usability, such as singular spectrum analysis and multi-ReliefF method. ResultsSixteen stroke survivors and ten healthy subjects were recruited for validation. Inspiring results of the proposed approach were achieved when compared with the clinical scores provided by a physiotherapist: 0.924 ± 0.027 for accuracy, 0.875 ± 0.063 for F1-score, 0.915 ± 0.051 for sensitivity, 0.969 ± 0.013 for specificity, 0.952 ± 0.038 for AUC, 0.098 ± 0.037 for mean absolute error, and 0.214 ± 0.078 for root mean squared error. ConclusionsThe results indicate that the proposed novel scoring approach can provide objective and accurate assessment scores, which can help physiotherapists make individualized treatment decisions.

Enhancing concrete structures education: Impact of virtual reality on motivation, performance and usability for undergraduate engineering students

AbstractBackground StudyThe research discusses the need for a paradigm shift in engineering education current practices to accommodate the digital native students. The paper emphasizes the importance of integrating disruptive technologies, namely Virtual Reality (VR) through Head Mounted Displays VR (HMD VR) and Desktop Based VR (DB VR) and comparing it with the traditional teaching methods. The research focuses on second‐year undergraduate students enrolled in a concrete structures course.ObjectivesThe objective of the study is to analyse the impact of DB VR and HMD VR on students' motivation, performance and workload in comparison with traditional 2D drawings. The study also aims to investigate how simulation sickness and system usability could impact students' motivation and performance when interpreting concrete structures.MethodsThe study divided second‐year civil engineering students into three groups, 2D, DB VR and HMD VR. The performance and motivation levels of students were assessed based on the number of mistakes identified and an intrinsic motivation survey. Furthermore, data on system usability and simulation sickness were collected. Spearman rank correlation was conducted to analyse the relationships between the variables tested.ResultsThe results have shown that students' motivation and performance were much higher when using VR in general and HMD VR specifically, students' efficiency and accuracy were also observed. On the other hand, usability was found to be moderately correlated with motivation, with students rating HMD VR as the most usable approach. A moderate inverse correlation was observed between simulation sickness and motivation, indicating that higher simulation sickness led to lower motivation levels.ConclusionThe study concludes that integrating VR in general, DB VR, or HMD VR into a concrete structures course for undergraduate students can significantly improve students' performance and motivation. Furthermore, enhancing usability of any of the methods used can also improve the performance and motivation. On the other hand, simulation sickness inversely affects motivation and performance, therefore, VR developers and educators should not neglect it.

Enhancing Usability of the Academic Information System at Bhayangkara University: A Design Thinking and System Usability Approach

Bhayangkara University implements an information system to assist its academic process, namely SIA (Academic Information System). The high level of usability in SIA affects the smooth running of the academic process. This research uses a combination of design thinking and system usability scale methods as an approach to increase usability in AIS applications. The results show that the SIA application has a high usability value with a B rating scale and the good acceptable category is pleasant for users. Recommendations for improvements based on the method used are increasing server capacity so that SIA can work more relevantly, and effectively, and can use last a long time

Comparison of Two Paradigms Based on Stimulation with Images in a Spelling Brain-Computer Interface.

A P300-based speller can be used to control a home automation system via brain activity. Evaluation of the visual stimuli used in a P300-based speller is a common topic in the field of brain-computer interfaces (BCIs). The aim of the present work is to compare, using the usability approach, two types of stimuli that have provided high performance in previous studies. Twelve participants controlled a BCI under two conditions, which varied in terms of the type of stimulus employed: a red famous face surrounded by a white rectangle (RFW) and a range of neutral pictures (NPs). The usability approach included variables related to effectiveness (accuracy and information transfer rate), efficiency (stress and fatigue), and satisfaction (pleasantness and System Usability Scale and Affect Grid questionnaires). The results indicated that there were no significant differences in effectiveness, but the system that used NPs was reported as significantly more pleasant. Hence, since satisfaction variables should also be considered in systems that potential users are likely to employ regularly, the use of different NPs may be a more suitable option than the use of a single RFW for the development of a home automation system based on a visual P300-based speller.

Proposal of a circularity design approach for urban factories based on local stakeholders’ engagement

Due to their bad image, factories have been pushed outside urban areas, making their supply networks wider with increasingly high environmental impacts. Although factories' implementation inside urban areas might be challenging with various constraints related to legislation, neighborhood, and higher rental costs, it can also be a great leveraging opportunity to increase resilience alongside created value, and reduce costs and negative impacts. This is mainly due to the concentration of circular economy actors inside urban areas, in addition to the availability of funding for sustainability-driven projects by local private and public institutions. The present paper proposes a design approach that provides urban factories with a set of local stakeholders’ engagement opportunities to enable circularity design throughout their value chain. A test of the approach has been conducted during 2 workshops with eco-design experts who were proposed with a case study of an urban factory in Grenoble. It has allowed the validation of the approach's usability and usefulness.

Effectiveness of Concussion Curriculum (CC) in Postgraduate Medical Education

Research Objectives Objectives: The aims of this review are to describe and assess the effects of concussion curriculum on medical learning. Design A systematic search of six databases (MEDLINE/ PUBMED, Ovid MEDLINE: Epub Ahead of Print, In-Process & Other Non-Indexed Citations, Ovid MEDLINE Daily and Ovid MEDLINE, Embase, ERIC, Cochrane, CINAHL) was conducted, using the text-word and MeSH-heading search strategy, in December 2021. Eligibility criteria included studies in a postgraduate education context that reported on the effects on learning. The validated MINORS (Methodological Index for Nonrandomized Studies) tool was utilized to assess the risk of bias. Kirkpatrick's evaluation model and Miller's assessment pyramid were used as frameworks to determine the impacts of CC on post-graduate learning. Setting Literature review. Participants N/A. Interventions Implementing a spiral curriculum following the systematic review of concussion curricula. Main Outcome Measures Competency. Results Six articles were identified, reporting on 2 retrospective studies and 4 cohort studies. Although there were mixed findings overall, the highest positive learning outcome reported was knowledge (Miller Level 1), and no studies assessed higher levels of curriculum impacts. Conclusions The effectiveness of CC in post-graduate medical education remains unknown regarding how the learning can be transferred to change practice and affect patient outcomes. Educational research should be built on conceptual frameworks and theories. Those with success employed constructivism, situated learning theory, and social learning theory/community of practice as the underpinning theories. To develop an effective CC, further prospective, competency-based concussion educational scholarship with mixed-method (quantitative and qualitative) evaluation is needed to capture curriculum processes and impacts over time. Using iterative usability approaches and medical educational frameworks, future CC research studies will be valuable to support competency-based medical education development. Author(s) Disclosures The authors of this study have no conflicts of interest to disclose and received no financial benefits. This research received no specific grant from any funding agency in public, commercial or not-for-profit sectors. Objectives: The aims of this review are to describe and assess the effects of concussion curriculum on medical learning. A systematic search of six databases (MEDLINE/ PUBMED, Ovid MEDLINE: Epub Ahead of Print, In-Process & Other Non-Indexed Citations, Ovid MEDLINE Daily and Ovid MEDLINE, Embase, ERIC, Cochrane, CINAHL) was conducted, using the text-word and MeSH-heading search strategy, in December 2021. Eligibility criteria included studies in a postgraduate education context that reported on the effects on learning. The validated MINORS (Methodological Index for Nonrandomized Studies) tool was utilized to assess the risk of bias. Kirkpatrick's evaluation model and Miller's assessment pyramid were used as frameworks to determine the impacts of CC on post-graduate learning. Literature review. N/A. Implementing a spiral curriculum following the systematic review of concussion curricula. Competency. Six articles were identified, reporting on 2 retrospective studies and 4 cohort studies. Although there were mixed findings overall, the highest positive learning outcome reported was knowledge (Miller Level 1), and no studies assessed higher levels of curriculum impacts. The effectiveness of CC in post-graduate medical education remains unknown regarding how the learning can be transferred to change practice and affect patient outcomes. Educational research should be built on conceptual frameworks and theories. Those with success employed constructivism, situated learning theory, and social learning theory/community of practice as the underpinning theories. To develop an effective CC, further prospective, competency-based concussion educational scholarship with mixed-method (quantitative and qualitative) evaluation is needed to capture curriculum processes and impacts over time. Using iterative usability approaches and medical educational frameworks, future CC research studies will be valuable to support competency-based medical education development.

Analysis of the usability quality of vocational high school websites using a user satisfaction approach

Purpose: knowing the extent to which aspects that affect the level of user/visitor satisfaction in using the website.methodology: the method used is usability approach to measure website visitor satisfaction using Structural Equation Model (SEM) theory and SmartPLS v.3.2.9 software.Findings/result: found several variables that influence user satisfaction, and found variables that had no effect, even having a negative dependency value. In addition, it also produces priority recommendations for website improvement to meet user satisfaction.Originality: this study uses the palmer model usability approach [13] and the structural equation model. Which is different from previous research using the webqual method and Importance Performance Analisys [3]

Perceived usability evaluation of learning management systems via axiomatic design with a real life application

PurposeUsage of learning management systems (LMSs) has become widespread with the disruption of face-to-face educations after the COVID-19 pandemic. There are several software products, usually named as LMS to enable and support distance education. However, selection of a suitable LMS is a complex multiple criteria decision making (MCDM) problem that requires consideration of many criteria and inputs from different parties like students, academicians, education managers, etc. Usability evaluation of LMS is one of the critical steps in deciding which LMS system to be adapted. There are several studies related to usability evaluation of LMS in the literature, but utilization of MCDM methods and real life case studies are very rare. Based on this motivation, perceived usability evaluation of SAKAI-LMS that is in use at an academic department is performed by employing axiomatic design procedure (ADP). This paper aims to discuss the aforementioned issues.Design/methodology/approachADP is considered as a suitable MCDM method for perceived usability evaluation as it allows an easy approach to data fusion and setting performance targets for decision makers. A questionnaire is developed to collect data from three types of system users about predetermined usability criteria and their importance. After detailed statistical analyses and weighting criteria via analytical hierarch process (AHP), ADP is carried out to evaluate usability of the LMS.FindingsIt is found that the proposed ADP based approach is easy to apply in practical circumstances and able to quantify perceived usability of the LMSs.Research limitations/implicationsThe proposed approach provides an easy and practical evaluation of perceived usability of the LMSs for decision makers who are responsible for the implementation of LMSs. The developed novel and practical MCDM-based perceived usability approach for LMS in this study has been verified through a real life case study at an academic department. Perceived usability results, therefore, reflects only the views of this focus group and are not generalizable.Originality/valueFirst time in the literature, a comprehensive ADP based MCDM approach is proposed based on the analyses of the related literature and information gathered from the system users.

Improving the User Experience with Discount Site-Specific User Testing.

Poor electronic health record (EHR) usability is associated with patient safety concerns, user dissatisfaction, and provider burnout. EHR certification requires vendors to perform user testing. However, there are no such requirements for site-specific implementations. Health care organizations customize EHR implementations, potentially introducing usability problems. Site-specific usability evaluations may help to identify these concerns, and "discount" usability methods afford health systems a means of doing so even without dedicated usability specialists. This report characterizes a site-specific discount user testing program launched at an academic medical center. We describe lessons learned and highlight three of the EHR features in detail to demonstrate the impact of testing on implementation decisions and on users. Thirteen new EHR features which had already undergone heuristic evaluation and iterative design were evaluated over the course of three user test events. Each event included five to six users. Participants used think aloud technique. Measures of user efficiency, effectiveness, and satisfaction were collected. Usability concerns were characterized by the type of usability heuristic violated and by correctability. Usability concerns occurred at a rate of 2.5 per feature tested. Seventy percent of the usability concerns were deemed correctable prior to implementation. The first highlighted feature was moved to production despite low single ease question (SEQ) scores which may have predicted its subsequent withdrawal from production based on post implementation feedback. Another feature was rebuilt based on usability findings, and a new version was retested and moved to production. A third feature highlights an easily correctable usability concern identified in user testing. Quantitative usability metrics generally reinforced qualitative findings. Simplified user testing with a limited number of participants identifies correctable usability concerns, even after heuristic evaluation. Our discount usability approach to site-specific usability has a role in implementations and may improve the usability of the EHR for the end user.

Towards a novel Business, Environmental and Social Screening Tool for Product-Service Systems (BESST PSS) design

Product-Service Systems (PSS) have recently regained attention in the literature and industry due to their potential to contribute to sustainability. PSS are also enjoying renewed attention, currently, as the large societal focus on circular economy (CE) enforces the potential of PSS. However, PSS are not more sustainable than traditional offerings by default and they, therefore, must be designed with sustainability in mind from the early design stages and their sustainability potential screened already at a conceptual design stage. Existing approaches to screen PSS sustainability have conspicuous shortcomings regarding their lack of comprehensiveness, usability and focus on the conceptual design stage deemed crucial for the sustainability level of the future offering. There is poor coverage, in the literature, of approaches to sustainability-driven PSS design, and no consolidated approach to supporting a comprehensive consideration of sustainability aspects in the early stages of PSS conceptualisation. This paper introduces a qualitative tool and a process that support decision-making through ex-ante screening of PSS concepts for manufacturing companies based on the triple-bottom-line (TBL) sustainable value potential over the PSS life cycle. The tool was developed iteratively through three action research cycles focused on theory development and theory testing, within a manufacturing company. The tool and the implementation process are perceived as an effective and efficient way to screen PSS concepts through a comprehensive, yet readily applicable and usable approach by the industry practitioners.

P06-14 Development of a standardised evaluation framework (SEF) for physical activity interventions: Ensuring usability and usefulness

IntroductionWith a range of interventions available for promoting physical activity (PA) and only limited resources, it has become imperative to identify those that are both effective and feasible for real world application. A number of evaluation frameworks have been developed but often fail to be widely implemented due to the level of information required and time needed to complete. The purpose of this study is to develop a standardised evaluation framework (SEF) for PA interventions that is usable in practice but also collects information that enables evidence based decision making among key knowledge users.MethodsDevelopment of the framework was guided by Nutbeam and Bauman's evaluation cycle, encompassing elements of formative, process, impact and outcome evaluation. The SEF was developed through four stages involving a 1) review of the literature, 2) feedback from key stakeholders, 3) national consultation, and 4) focus groups with a practitioner advisory group. Elements of the Technology Acceptance Model were used to assess the perceived usefulness and usability of the SEF by key stakeholders.††ResultsTwelve relevant evaluation frameworks specific to PA interventions were identified through the literature review. Members of the project team (N = 3) identified commonalities across these frameworks, including general characteristics (N = 12), formative evaluation aspects (N = 5), process evaluation aspects (N = 15), impact evaluation aspects (N = 7) and outcome evaluation aspects (N = 3). Feedback across four stages, including consultations, two focus groups and an online survey provided feedback for creating a more usable and useful SEF. The current framework includes a minimum set of questions (i.e. monitoring template) for coordinators (N = 27) and participants (N = 9) with additional measures available for an in-depth evaluation where necessary.ConclusionI-PARC has seen the creation of a SEF that is moving towards a more usable approach for intervention evaluation in practice. The I-PARC SEF has the potential to be a usable resource to assess current PA interventions and provide knowledge regarding the potential scale up, adaptions or cessation of current practices. Feedback has also suggested a need for an online platform to collect the relevant information, capacity building resources and a support network to help with the use of the I-PARC SEF.

Exploiting auto-encoders for explaining black-box classifiers

Recent years have witnessed the rise of accurate but obscure classification models that hide the logic of their internal decision processes. In this paper, we present a framework to locally explain any type of black-box classifiers working on any data type through a rule-based model. In the literature already exists local explanation approaches able to accomplish this task. However, they suffer from a significant limitation that implies representing data as a binary vectors and constraining the local surrogate model to be trained on synthetic instances that are not representative of the real world. We overcome these deficiencies by using autoencoder-based approaches. The proposed framework first allows to generate synthetic instances in the latent feature space and learn a latent decision tree classifier. After that, it selects and decodes the synthetic instances respecting local decision rules. Independently from the data type under analysis, such synthetic instances belonging to different classes can unveil the reasons for the classification. Also, depending on the data type, they can be exploited to provide the most useful kind of explanation. Experiments show that the proposed framework advances the state-of-the-art towards a comprehensive and widely usable approach that is able to successfully guarantee various properties besides interpretability.