Filters








107,706 Hits in 4.0 sec

Storyboard-Based Empirical Modelling of Touch Interface Performance

Alix Goguey, Géry Casiez, Andy Cockburn, Carl Gutwin
2018 Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems - CHI '18  
For rapid prototyping, most applications only support visual design.  ...  Touch interactions are now ubiquitous, but few tools are available to help designers quickly prototype touch interfaces and predict their performance.  ...  Discussion StEM is designed to integrate support for rapid prototyping of touch interactions with the benefits of accurate performance prediction.  ... 
doi:10.1145/3170427.3186479 dblp:conf/chi/GogueyCCG18a fatcat:zr2v6b2p75b2lnelfgdezjfrfi

Classification of Random Forms and Distortions Presented to the Left or Right Visual Field

Seymour Axelrod, Lillian Leiber, Michael Noonan
1978 Perceptual and Motor Skills  
Accuracy of performance on positive items increased in the order New < Old < Prototype.  ...  More false alarms occurred to unrelated items in the right than in the left visual field, suggesting that the trace systems generated during training had different characteristics in the two hemispheres  ...  The Prototypes elicited more accurate performance than even the Old items, i.e., the Prototypes were more obviously members of the appropriate categories than the distortions actually experienced.  ... 
doi:10.2466/pms.1978.47.2.615 pmid:724400 fatcat:55smn7alhfcq7ev3nrvwcoavjq

Attribute Prototype Network for Zero-Shot Learning [article]

Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, Zeynep Akata
2021 arXiv   pre-print
While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate  ...  To this end, we propose a novel zero-shot representation learning framework that jointly learns discriminative global and local features using only class-level attributes.  ...  As the baseline, we train a single BaseMod with cross-entropy loss L CLS , and use gradient-based visual explanation method CAM [54] to investigate the image area BaseMod used to predict each attribute  ... 
arXiv:2008.08290v4 fatcat:wegnue3l45hw5n4job6l2txb44

Revel8or: Model Driven Capacity Planning Tool Suite

Liming Zhu, Yan Liu, Ngoc Bao Bui, Ian Gorton
2007 Proceedings / International Conference of Software Engineering  
DSLBench allows the same benchmark modeling and generation to be conducted using a simple performance engineering Domain Specific Language (DSL) in Microsoft Visual Studio.  ...  Ideally, the application architect could derive accurate performance predictions early in the project life-cycle, leveraging initial application design-level models and a description of the target software  ...  Our aim was to assess the performance potential of the Web services involved. We were able to use the MDABench prototype in the measurement planning phase.  ... 
doi:10.1109/icse.2007.73 dblp:conf/icse/ZhuLBG07 fatcat:2vmystufsrcf5e3wcfik6m5uce

Predicting Student's Performance Through Data Mining [article]

Aaditya Bhusal
2021 arXiv   pre-print
Predicting the performance of students early and as accurately as possible is one of the biggest challenges of educational institutions.  ...  Using machine learning the student's performance can be predicted with the help of students' data collected from Learning Management Systems (LMS).  ...  Prototype The prototype system used in this project is taken from a Jupyter notebook from Kaggle that uses a popular dataset related to students' academic performance from Kaggle [11] .  ... 
arXiv:2112.01247v1 fatcat:gacgyctqfbfn7dc4fcgjgvv7hm

MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation [article]

Ehtesham Iqbal, Sirojbek Safarov, Seongdeok Bang
2022 arXiv   pre-print
Prototype learning, where the support feature yields a singleor several prototypes by averaging global and local object information, has been widely used in FSS.  ...  The multi-similarity module exploits multiple feature-maps of support images and query images to estimate accurate semantic relationships.  ...  Whereas, the visual correspondences-based models [36] performed K time forward pass and got prediction mask using threshold-based method.  ... 
arXiv:2206.09667v1 fatcat:jm3it3uk5vhcvbcc5ymnzzvape

Applying Ensemble Learning Algorithm in Early Prognosis of Heart Illness

Lijetha.C. Jaffrin, Et. al.
2021 Turkish Journal of Computer and Mathematics Education  
In this paper, Random Forest and AdaBoost ensemble Machine Learning Procedures are used in advance to predict heart disease.  ...  Predicting and diagnosing heart disease is a daunting aspect faced by physicians and hospitals around the world.  ...  This paper [6] explored the practice of hybrid ensemble prototype in which accurate ensemble is proposed than simple collaborative prototypes, leading to better results than other models of prediction  ... 
doi:10.17762/turcomat.v12i2.1513 fatcat:nefiirbf35gsrlg6ktyy6jztea

Modeling Object Recognition in Newborn Chicks using Deep Neural Networks [article]

Donsuk Lee, Denizhan Pak, Justin N. Wood
2021 arXiv   pre-print
Since newborn animals learn largely through unsupervised learning, we explored whether unsupervised learning algorithms can be used to predict the view-invariant object recognition behavior of newborn  ...  We show that features derived from unsupervised DNNs make competitive predictions about chick behavior compared to supervised features.  ...  Figure 3 : 3 Figure 3: Actual task performance of the chicks (dotted lines) and predicted task performance of the models (blue lines).  ... 
arXiv:2106.07185v1 fatcat:avpnq32siveq5l5ilx6eei26my

Visual and auditory processing of common pattern class structure

Leona S. Aiken, Lawrence R. Griffin
1972 Perception & Psychophysics  
If Ss were using the "A" vs "non-A" strategy, then only the extent to which they had accurately learned the A prototype should correlate with their performance.  ...  Performance in Group V1-A2 for visual classification was quite accurate.  ... 
doi:10.3758/bf03210942 fatcat:6eldnh4edjf7llxseh2wslstfm

The Assessment of Basic Learning Abilities Test for Predicting Learning of Persons With Intellectual Disabilities

Garry L. Martin, Jennifer R. Thorsteinsson, C.T. Yu, Toby L. Martin, Tricia Vause
2008 Behavior Modification  
The authors review studies that have examined performance of participants with developmental disabilities (DD) on the ABLA test to predict (a) performance on a variety of simple imitations and two-choice  ...  Across all five types of studies, the predictive validity of the ABLA test has been very high.  ...  The ABLA test was least accurate for predicting performance of participants at ABLA Level 3, the two-choice visual discrimination.  ... 
doi:10.1177/0145445507309022 pmid:18285508 fatcat:hw6q35tayjhcpilg7gcf76xz3u

The Predictive Power of Internet-Based Product Concept Testing Using Visual Depiction and Animation

Ely Dahan, V. Srinivasan
2000 The Journal of product innovation management  
We measure the predictive accuracy of Internet-based product concept testing that incorporates virtual prototypes of new products.  ...  As virtual prototypes cost considerably less to build and test than their physical counterparts, design teams using Internet-based product concept research can afford to explore a much larger number of  ...  It remains to be seen which goods are best suited to virtual, visual testing, but we expect that many durable good categories can be accurately represented using VRML animation and compared using the simulated  ... 
doi:10.1111/1540-5885.1720099 fatcat:o6jfw3a2rzgllibp5izvwqhxzy

Attribute Prototype Network for Any-Shot Learning [article]

Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, Zeynep Akata
2022 arXiv   pre-print
While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate  ...  To this end, we propose a novel representation learning framework that jointly learns discriminative global and local features using only class-level attributes.  ...  As the baseline, we train a single BaseMod with crossentropy loss L CLS , and use gradient-based visual explanation method CAM (Zhou et al., 2016) to investigate the image area BaseMod used to predict  ... 
arXiv:2204.01208v1 fatcat:eljtv3zgt5db3bwcshvfn2wx54

A Virtual Prototype for Fast Design and Visualization of Gerotor Pumps

Juan Pareja-Corcho, Aitor Moreno, Bruno Simoes, Asier Pedrera-Busselo, Ekain San-Jose, Oscar Ruiz-Salguero, Jorge Posada
2021 Applied Sciences  
CFD methods are accurate in predicting the behavior of the pump, at the expense of large computing resources and time.  ...  In response to the current status, this manuscript reports a virtual prototype to be used in the context of a Digital Twin tool.  ...  The CFD simulations are currently used in most of the design processes as an accurate prediction of the pump's performance. Therefore, they are a valid point of comparison for our implementation.  ... 
doi:10.3390/app11031190 fatcat:6pblanmjw5hnrmjkmrd5o7v7ve

Improve credit scoring using transfer of learned knowledge from self-organizing map

Ali AghaeiRad, Ning Chen, Bernardete Ribeiro
2016 Neural computing & applications (Print)  
A complete and unique graphical visualization technique is shown which better outlines the trade-off between distinct metrics and attained performance.  ...  This gives some insights on how to construct more accurate predictive models when the data collection is difficult in some financial applications.  ...  The rational behind using SOM prior to FNN is that the prototypes found by SOM usually represent the center of clusters and therefore contribute to constructing accurate classification models.  ... 
doi:10.1007/s00521-016-2567-2 fatcat:rpig4oeqpnarrjlknkgxfv6uky

SLEEPER: interpretable Sleep staging via Prototypes from Expert Rules [article]

Irfan Al-Hussaini, Cao Xiao, M. Brandon Westover, Jimeng Sun
2019 arXiv   pre-print
In this study, we propose Sleep staging via Prototypes from Expert Rules (SLEEPER), which combines deep learning models with expert defined rules using a prototype learning framework to generate simple  ...  We evaluated SLEEPER using two PSG datasets collected from sleep studies and demonstrated that SLEEPER could provide accurate sleep stage classification comparable to human experts and deep neural networks  ...  In this paper, we present SLEEPER that introduces a deep prototype learning method that provides accurate predictions as well as very simple and intuitive prediction models with a shallow decision tree  ... 
arXiv:1910.06100v1 fatcat:fjk6j5mehbgsvee4iiy6bfxgkq
« Previous Showing results 1 — 15 out of 107,706 results