Abstract. The design of user interfaces plays an important role in human computer interaction, especially for smartphones and tablet devices. It is very important to consider the interface design of smartphones for elderly people in order for them to benefit from the variety applications on such devices. The aim of this study is to investigate the effects of user age as well as screen size on smartphone/tablet use. We evaluated the usability of smartphone interfaces for three different age groups: elderly age group (60+ years), middle age group (40-59 years) and younger age group (20-39 years). The evaluation is performed using three different screen sizes of smartphone and tablet devices: 3.2", 7", and 10.1" respectively. An eye-tracker device was employed to obtain three metrics: fixation duration, scan-path duration, and saccades amplitude. Two hypothesis were considered. First, elderly users will have both local and global processing diffieculties on smartphone/tablet use than other age groups. Second, all user age groups will be influnced by screen sizes; small screen size will have smaller saccades proportion indicating uneasy interface broswing compared to large screen size. All these results have been statistically evaluated using 2-way ANOVA.

Abstract-This paper presents methodology for user identification on smartphone and mini-tablet using finger based gestures. In this paper, a set of four features, namely Signature Precision (SP), Finger Pressure (FP), Movement Time (MT), and Speed were extracted from each gesture of eight using dynamic time warping and Euclidean distance. The features are then used individually and combined for the purpose of user identification based on the Euclidean distance and the k-nearest neighbour classifier. We concluded that the best identification accuracy results from the combinations of FP and MT features where 78.46% and 78.33% were achieved on small smartphone and Minitablet respectively using a dataset of 50 users.

In this paper we investigated the possibility of classifying users' age-group using gesture-based features on smartphones. The features used were gesture accuracy, speed, movement time, and finger/force pressure. Nearest Neighbour classification was used to classify a given user's age-group. The 50 participants involved in this research included 25 elderly and 25 younger users. User-dependent and user-independent age-group classification scenarios were considered. On each scenario, two types of analysis were considered; using a single-feature and combined-features to represent a user-age group. The results revealed that classification accuracy was relatively higher for the younger age group than the elderly age group. Also, a higher classification accuracy was achieved on the small smartphone than on mini-tablets. The results also showed that the classification accuracy increases when combining the gesture features in to a single representation as opposed to using a single gesture feature.

Identifying birds is one of challenging role for bird watchers due to the similarity of the birds' forms/image background and the lack of experience for watchers. So, it needs a computer system based images to help birdwatchers in order to identify birds. This study aims at investigating the use of deep learning for birds' identification using convolutional neural network for extracting features from images. The investigation was performed on database contained 4340 images that collected by the paper author from Jordan. The Principal Component Analysis (was applied on layer 6 and 7, as well as on the statistical operations of merging the two layers like: average, minimum, maximum and combine of both layers. The datasets were investigated by the following classifiers: Artificial neural networks, K-Nearest Neighbor, Random Forest, Naïve Bayes and Decision Tree. Whereas, the metrics used in each classifier are: accuracy, precision, recall, and F-Measure. The results of investigation include and not limited to the following, the PCA used on the deep features does not only reduce the dimensionality, and therefore, the training/testing time is reduced significantly, but also allows for increasing the identification accuracy, particularly when using the Artificial Neural Networks classifier. Based on the results of classifiers; Artificial neural networks showed high classification accuracy (70.9908), precision (0.718), recall (0.71) and F-Measure (0.708) compared to other classifiers.

No abstract