Solutions documentation

Crawford, Vanadis; Pitts, Angela; Radcliffe, Rosalind; Seifert, Leah Ann

doi:10.1145/1026533.1026552

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[5] Installation procedures are often performed with the help of wizards, so that most of the necessary configuration tasks are hidden from the user in the typical process. When installation cannot follow the typical path, it tends to be a very complex activity that may require lots of work [6].…”

Section: Installation Interface Usabilitymentioning

confidence: 99%

Accessibility of Assistive Software Installation Interfaces

Filgueiras

Sales

Gruenwald

et al. 2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Software installation is a one-time task; yet, it should work well. Regarding assistive technologies, users with disabilities will often require help in installation tasks. Five assistive software products were evaluated in order to identify barriers faced by visually impaired users performing the installation task and none of them, for different reasons, allowed full completion of installation task. Some recommendations are devised from the experience.

show abstract

Section: Installation Interface Usabilitymentioning

confidence: 99%

Accessibility of Assistive Software Installation Interfaces

Filgueiras

Sales

Gruenwald

et al. 2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

Forecasting water levels at the Yangtze River with neural networks

Hartmann¹,

Becker²,

King³

et al. 2008

erd

View full text Add to dashboard Cite

In the last ten years, the application of neural network models has become an emerging field of research in the field of hydrology. In the present study, three different neural network models, namely the Multilayer Perceptron (MLP), the Jordan net, and the Elman net were used for forecasting water levels at Cuntan station, located at the Yangtze River's upper reaches. The performances of the neural network models were compared with each other and with the results of a multiple linear regression (MLR) model. As input variables for the models, not only were precipitation data and antecedent water levels implemented, but also two climatic variables which are usually left out in the field of neural network modeling: evaporation and snow data. Before the models were adopted, the optimal lead time between the input variables and the model output was determined by means of a cross-correlation analysis. The highly significant correlation between the model input and output already indicated a highly linear relationship. Accordingly, the MLR model showed the best performance, even though the results of the other models are only slightly worse. The good capability of the Jordan net in forecasting high water levels should be investigated further. In predicting water levels in general, the integrated snow data improved the performance of the different models only marginally. However, the integration of evaporation data definitely improved the modeling results. Zusammenfassung: In den vergangenen zehn Jahren hat die Anwendung neuronaler Netze in der Hydrologie zunehmend an Bedeutung gewonnen. In der vorliegenden Studie wurden drei verschiedene neuronale Netzwerkmodelle, namentlich das Multilayer Perzeptron, das Jordan-und das Elman-Netz, eingesetzt, um die Wasserstände an der hydrologischen Station Cuntan (Yangtze-Oberlauf) zu simulieren. Die erzielte Modellgüte der unterschiedlichen Netztypen wurde sowohl untereinander als auch mit den Ergebnissen eines multiplen linearen Regressionsmodells verglichen. Als Eingangsvariablen wurden über die für neuronale Netzwerkmodelle üblichen Eingangsvariablen Niederschlag und Wasserstände der vorherigen Zeitschritte hinaus Verdunstungs-und Schneedaten integriert. Bevor die Modelle eingesetzt wurden, wurde mittels einer Kreuzkorrelationsanalyse der optimale Zeitabstand zwischen den Eingangvariablen und der Modellausgabe berechnet. Die Ergebnisse dieser Korrelationsanalyse zeigen eine hochsignifikante Korrelation und weisen damit auf eine lineare Relation hin. Aufgrund dieser linearen Relation zeigt das multiple lineare Regressionsmodel das beste Resultat, auch wenn die Ergebnisse der anderen Modelle nur als geringfügig schlechter einzuordnen sind. Die gute Leistungsfähigkeit des Jordan-Netzes bei der Simulation der hohen Wasserstände sollte in zukünftigen Studien vertieft untersucht werden. Bei der Simulation sämtlicher Wasserstände konnte durch die Integration der Schneedaten lediglich eine marginale Verbesserung der Modellgüte erzielt werden; mit der Implementierung der Verdunstungsdaten ...

show abstract

Solutions documentation

Cited by 2 publications

References 0 publications

Accessibility of Assistive Software Installation Interfaces

Accessibility of Assistive Software Installation Interfaces

Forecasting water levels at the Yangtze River with neural networks

Contact Info

Product

Resources

About