No abstract

No abstract

No abstract

No abstract

Fisher kernels derived from stochastic probabilistic models such as restricted and deep Boltzmann machines have shown competitive visual classification results in comparison to widely popular deep discriminative models. This genre of Fisher kernels bridges the gap between shallow and deep learning paradigm by inducing the characteristics of deep architecture into Fisher kernel, further deployed for classification in discriminative classifiers. Despite their success, the memory and computational costs of Fisher vectors do not make them amenable for large‐scale visual retrieval and classification tasks. This study introduces a novel feature selection technique inspired from the functional characteristics of neural architectures for learning discriminative feature representations to boost the performance of Fisher kernels against deep discriminative models. The proposed technique condenses the large dimensional Fisher features for kernel learning and shows improvement in its classification performance and storage cost on leading benchmark data sets. A comparison of the proposed method with other state‐of‐the‐art feature selection techniques is made to demonstrate its performance supremacy as well as time complexity required to learn in reduced Fisher space.

Wayfinding presents a significant aspect in architectural design since it is associated with the spatial organization and the legibility of indoor environments. It is believed that the physical characteristics of the indoor environment influence the performance of individuals in finding their way in complex settings. Navigation in such buildings can be a distressing process if the needed spatial information is not clearly presented to users; hence, it is important during the design phase to consider the factors that affect users' wayfinding performance. This paper examines these factors in indoor environments and focuses on the design variables that influence their legibility. Furthermore, it attempts to develop a quantitative evaluation model that assesses wayfinding in complex buildings in terms of their architectural design variables, through assigning weights of importance to these variables. For the purpose of implementing and testing the evaluation model, two case studies were conducted in shopping centers in Cairo, Egypt. The performance of users during the study was found to be consistent with the results of the evaluation model. This suggests that the assigned weights of the design variables were rather logical. These weights help in defining the design priorities for wayfinding: building configuration and its complexity are regarded as the first priority, followed by architectural differentiation, visual accessibility, and lastly, landmarks.

No abstract

No abstract