expert knowledge
Recently Published Documents





Clara Pereira ◽  
João N. Silva ◽  
Ana Silva ◽  
Jorge de Brito ◽  
José D. Silvestre

2022 ◽  
Vol 29 (3) ◽  
pp. 1-34
Moritz Alexander Messerschmidt ◽  
Sachith Muthukumarana ◽  
Nur Al-Huda Hamdan ◽  
Adrian Wagner ◽  
Haimo Zhang ◽  

We present ANISMA, a software and hardware toolkit to prototype on-skin haptic devices that generate skin deformation stimuli like pressure, stretch, and motion using shape-memory alloys (SMAs). Our toolkit embeds expert knowledge that makes SMA spring actuators more accessible to human–computer interaction (HCI) researchers. Using our software tool, users can design different actuator layouts, program their spatio-temporal actuation and preview the resulting deformation behavior to verify a design at an early stage. Our toolkit allows exporting the actuator layout and 3D printing it directly on skin adhesive. To test different actuation sequences on the skin, a user can connect the SMA actuators to our customized driver board and reprogram them using our visual programming interface. We report a technical analysis, verify the perceptibility of essential ANISMA skin deformation devices with 8 participants, and evaluate ANISMA regarding its usability and supported creativity with 12 HCI researchers in a creative design task.

2022 ◽  
Vol 19 (1) ◽  
pp. 1-25
Hongzhi Liu ◽  
Jie Luo ◽  
Ying Li ◽  
Zhonghai Wu

Pass selection and phase ordering are two critical compiler auto-tuning problems. Traditional heuristic methods cannot effectively address these NP-hard problems especially given the increasing number of compiler passes and diverse hardware architectures. Recent research efforts have attempted to address these problems through machine learning. However, the large search space of candidate pass sequences, the large numbers of redundant and irrelevant features, and the lack of training program instances make it difficult to learn models well. Several methods have tried to use expert knowledge to simplify the problems, such as using only the compiler passes or subsequences in the standard levels (e.g., -O1, -O2, and -O3) provided by compiler designers. However, these methods ignore other useful compiler passes that are not contained in the standard levels. Principal component analysis (PCA) and exploratory factor analysis (EFA) have been utilized to reduce the redundancy of feature data. However, these unsupervised methods retain all the information irrelevant to the performance of compilation optimization, which may mislead the subsequent model learning. To solve these problems, we propose a compiler pass selection and phase ordering approach, called Iterative Compilation based on Metric learning and Collaborative filtering (ICMC) . First, we propose a data-driven method to construct pass subsequences according to the observed collaborative interactions and dependency among passes on a given program set. Therefore, we can make use of all available compiler passes and prune the search space. Then, a supervised metric learning method is utilized to retain useful feature information for compilation optimization while removing both the irrelevant and the redundant information. Based on the learned similarity metric, a neighborhood-based collaborative filtering method is employed to iteratively recommend a few superior compiler passes for each target program. Last, an iterative data enhancement method is designed to alleviate the problem of lacking training program instances and to enhance the performance of iterative pass recommendations. The experimental results using the LLVM compiler on all 32 cBench programs show the following: (1) ICMC significantly outperforms several state-of-the-art compiler phase ordering methods, (2) it performs the same or better than the standard level -O3 on all the test programs, and (3) it can reach an average performance speedup of 1.20 (up to 1.46) compared with the standard level -O3.

2022 ◽  
Vol 14 (2) ◽  
pp. 393
Mike Teucher ◽  
Detlef Thürkow ◽  
Philipp Alb ◽  
Christopher Conrad

Digital solutions in agricultural management promote food security and support the sustainable use of resources. As a result, remote sensing (RS) can be seen as an innovation for the fast generation of reliable information for agricultural management. Near real-time processed RS data can be used as a tool for decision making on multiple scales, from subplot to the global level. This high potential is not yet fully applied, due to often limited access to ground truth information, which is crucial for the development of transferable applications and acceptance. In this study we present a digital workflow for the acquisition, processing and dissemination of agroecological information based on proprietary and open-source software tools with state-of-the-art web-mapping technologies. Data is processed in near real-time and thus can be used as ground truth information to enhance quality and performance of RS-based products. Data is disseminated by easy-to-understand visualizations and download functionalities for specific application levels to serve specific user needs. It thus can increase expert knowledge and can be used for decision support at the same time. The fully digital workflow underpins the great potential to facilitate quality enhancement of future RS products in the context of precision agriculture by safeguarding data quality. The generated FAIR (findable, accessible, interoperable, reusable) datasets can be used to strengthen the relationship between scientists, initiatives and stakeholders.

2022 ◽  
Vol 15 ◽  
Ying Chu ◽  
Guangyu Wang ◽  
Liang Cao ◽  
Lishan Qiao ◽  
Mingxia Liu

Resting-state functional MRI (rs-fMRI) has been widely used for the early diagnosis of autism spectrum disorder (ASD). With rs-fMRI, the functional connectivity networks (FCNs) are usually constructed for representing each subject, with each element representing the pairwise relationship between brain region-of-interests (ROIs). Previous studies often first extract handcrafted network features (such as node degree and clustering coefficient) from FCNs and then construct a prediction model for ASD diagnosis, which largely requires expert knowledge. Graph convolutional networks (GCNs) have recently been employed to jointly perform FCNs feature extraction and ASD identification in a data-driven manner. However, existing studies tend to focus on the single-scale topology of FCNs by using one single atlas for ROI partition, thus ignoring potential complementary topology information of FCNs at different spatial scales. In this paper, we develop a multi-scale graph representation learning (MGRL) framework for rs-fMRI based ASD diagnosis. The MGRL consists of three major components: (1) multi-scale FCNs construction using multiple brain atlases for ROI partition, (2) FCNs representation learning via multi-scale GCNs, and (3) multi-scale feature fusion and classification for ASD diagnosis. The proposed MGRL is evaluated on 184 subjects from the public Autism Brain Imaging Data Exchange (ABIDE) database with rs-fMRI scans. Experimental results suggest the efficacy of our MGRL in FCN feature extraction and ASD identification, compared with several state-of-the-art methods.

Paula Hatum ◽  
Kathryn McMahon ◽  
Kerrie Mengersen ◽  
Paul Wu

Ecological models are extensively and increasingly used in support of environmental policy and decision making. Dynamic Bayesian Networks (DBN) as a tool for conservation have been demonstrated to be a valuable tool for providing a systematic and intuitive approach to integrating data and other critical information to help guide the decision-making process. However, data for a new ecosystem are often sparse. In this case, a general DBN developed for similar ecosystems could be applicable, but this may require the adaptation of key elements of the network. The research presented in this paper focused on a case study to identify and implement guidelines for model adaptation. We adapted a general DBN of a seagrass ecosystem to a new location where nodes were similar, but the conditional probability tables varied. We focused on two species of seagrass (Zostera noltei and Z. marina) located in Arcachon Bay, France. Expert knowledge was used to complement peer-reviewed literature to identify which components needed adjustment including parameterisation and quantification of the model and desired outcomes. We adopted both linguistic labels and scenario-based elicitation to elicit from experts the conditional probabilities used to quantify the DBN. Following the proposed guidelines, the model structure of the DBN was retained, but the conditional probability tables were adapted for nodes that characterised the growth dynamics in Zostera spp. population located in Arcachon Bay, as well as the seasonal variation on their reproduction. Particular attention was paid to the light variable as it is a crucial driver of growth and physiology for seagrasses. Our guidelines provide a way to adapt a general DBN to specific ecosystems to maximise model reuse and minimise re-development effort. Especially important from a transferability perspective are guidelines for ecosystems with limited data, and how simulation and prior predictive approaches can be used in these contexts.

10.2196/27631 ◽  
2022 ◽  
Vol 9 (1) ◽  
pp. e27631
Kate M Gunn ◽  
Gemma Skaczkowski ◽  
James Dollman ◽  
Andrew D Vincent ◽  
Camille E Short ◽  

Background Farming is physically and psychologically hazardous. Farmers face many barriers to help seeking from traditional physical and mental health services; however, improved internet access now provides promising avenues for offering support. Objective This study aims to co-design with farmers the content and functionality of a website that helps them adopt transferable coping strategies and test its acceptability in the broader farming population. Methods Research evidence and expert opinions were synthesized to inform key design principles. A total of 18 farmers detailed what they would like from this type of website. Intervention logic and relevant evidence-based strategies were mapped. Website content was drafted and reviewed by 2 independent mental health professionals. A total of 9 farmers provided detailed qualitative feedback on the face validity of the draft content. Subsequently, 9 farmers provided feedback on the website prototype. Following amendments and internal prototype testing and optimization, prototype usability (ie, completion rate) was examined with 157 registered website users who were (105/157, 66.9%) female, aged 21-73 years; 95.5% (149/156) residing in inner regional to very remote Australia, and 68.2% (107/157) “sheep, cattle and/or grain farmers.” Acceptability was examined with a subset of 114 users who rated at least module 1. Interviews with 108 farmers who did not complete all 5 modules helped determine why, and detailed interviews were conducted with 18 purposively sampled users. Updates were then made according to adaptive trial design methodology. Results This systematic co-design process resulted in a web-based resource based on acceptance and commitment therapy and designed to overcome barriers to engagement with traditional mental health and well-being strategies—ifarmwell. It was considered an accessible and confidential source of practical and relevant farmer-focused self-help strategies. These strategies were delivered via 5 interactive modules that include written, drawn, and audio- and video-based psychoeducation and exercises, as well as farming-related jokes, metaphors, examples, and imagery. Module 1 included distress screening and information on how to speak to general practitioners about mental health–related concerns (including a personalized conversation script). Modules were completed fortnightly. SMS text messages offered personalized support and reminders. Qualitative interviews and star ratings demonstrated high module acceptability (average 4.06/5 rating) and suggested that additional reminders, higher quality audio recordings, and shorter modules would be useful. Approximately 37.1% (52/140) of users who started module 1 completed all modules, with too busy or not got to it yet being the main reason for non-completion, and previous module acceptability not predicting subsequent module completion. Conclusions Sequential integration of research evidence, expert knowledge, and farmers’ preferences in the co-design process allowed for the development of a self-help intervention that focused on important intervention targets and was acceptable to this difficult-to-engage group. Trial Registration Australian New Zealand Clinical Trials Registry ACTRN12617000506392;

PLoS ONE ◽  
2022 ◽  
Vol 17 (1) ◽  
pp. e0261621
Nerea Almeda ◽  
Carlos R. Garcia-Alonso ◽  
Mencia R. Gutierrez-Colosia ◽  
Jose A. Salinas-Perez ◽  
Alvaro Iruin-Sanz ◽  

Major efforts worldwide have been made to provide balanced Mental Health (MH) care. Any integrated MH ecosystem includes hospital and community-based care, highlighting the role of outpatient care in reducing relapses and readmissions. This study aimed (i) to identify potential expert-based causal relationships between inpatient and outpatient care variables, (ii) to assess them by using statistical procedures, and finally (iii) to assess the potential impact of a specific policy enhancing the MH care balance on real ecosystem performance. Causal relationships (Bayesian network) between inpatient and outpatient care variables were defined by expert knowledge and confirmed by using multivariate linear regression (generalized least squares). Based on the Bayesian network and regression results, a decision support system that combines data envelopment analysis, Monte Carlo simulation and fuzzy inference was used to assess the potential impact of the designed policy. As expected, there were strong statistical relationships between outpatient and inpatient care variables, which preliminarily confirmed their potential and a priori causal nature. The global impact of the proposed policy on the ecosystem was positive in terms of efficiency assessment, stability and entropy. To the best of our knowledge, this is the first study that formalized expert-based causal relationships between inpatient and outpatient care variables. These relationships, structured by a Bayesian network, can be used for designing evidence-informed policies trying to balance MH care provision. By integrating causal models and statistical analysis, decision support systems are useful tools to support evidence-informed planning and decision making, as they allow us to predict the potential impact of specific policies on the ecosystem prior to its real application, reducing the risk and considering the population’s needs and scientific findings.

2022 ◽  
Vol 14 (2) ◽  
pp. 308
Zhao Zhan ◽  
Wenzhong Shi ◽  
Min Zhang ◽  
Zhewei Liu ◽  
Linya Peng ◽  

Landslide trails are important elements of landslide inventory maps, providing valuable information for landslide risk and hazard assessment. Compared with traditional manual mapping, skeletonization methods offer a more cost-efficient way to map landslide trails, by automatically generating centerlines from landslide polygons. However, a challenge to existing skeletonization methods is that expert knowledge and manual intervention are required to obtain a branchless skeleton, which limits the applicability of these methods. To address this problem, a new workflow for landslide trail extraction (LTE) is proposed in this study. To avoid generating redundant branches and to improve the degree of automation, two endpoints, i.e., the crown point and the toe point, of the trail were determined first, with reference to the digital elevation model. Thus, a fire extinguishing model (FEM) is proposed to generate skeletons without redundant branches. Finally, the effectiveness of the proposed method is verified, by extracting landslide trails from landslide polygons of various shapes and sizes, in two study areas. Experimental results show that, compared with the traditional grassfire model-based skeletonization method, the proposed FEM is capable of obtaining landslide trails without spurious branches. More importantly, compared with the baseline method in our previous work, the proposed LTE workflow can avoid problems including incompleteness, low centrality, and direction errors. This method requires no parameter tuning and yields excellent performance, and is thus highly valuable for practical landslide mapping.

Muhammad Akram ◽  
Ghous Ali ◽  
José Carlos R. Alcantud ◽  
Aneesa Riaz

AbstractWith the rapid growth of population, the global impact of solar technology is increasing by the day due to its advantages over other power production technologies. Demand for solar panel systems is soaring, thus provoking the arrival of many new manufacturers. Sale dealers or suppliers face an uncertain problem to choose the most adequate technological solution. To effectively address such kind of issues, in this paper we propose the Fermatean fuzzy soft expert set model by combining Fermatean fuzzy sets and soft expert sets. We describe this hybrid model with numerical examples. From a theoretical standpoint, we demonstrate some essential properties and define operations for this setting. They comprise the definitions of complement, union and intersection, the OR operation and the AND operation. Concerning practice in this new environment, we provide an algorithm for multi-criteria group decision making whose productiveness and authenticity is dutifully tested. We explore a practical application of this approach (that is, the selection of a suitable brand of solar panel system). Lastly, we give a comparison of our model with certain related mathematical tools, including fuzzy and intuitionistic fuzzy soft expert set models.

Sign in / Sign up

Export Citation Format

Share Document