… deep learning frameworks, mobile devices, … deep learning frameworks, such as Caffe2 [13]
and TensorFlow Lite [19], support executing deep learning models directly on mobile devices. …

… If mobile CNN models are to achieve their promise it is … mobile devices in conditions they
are intended to be used in. Here, we investigate plant disease diagnostics on a mobile device. …

… DNN models trained by deep learning frameworks such as Caffe [23] or Tensorflow. To run
the partitioned DNN models on CPU, we use the Caffe deep learning framework. Since the …

… The available bandwidth between the edge server and the mobile device is controlled by
the WonderShaper [10] tool. As for the deep learning framework, we choose Chainer [11] that …

… First, we present a set of parallel processing optimizations to accelerate deep learning
computation on mobile devices. Second, our framework addresses three issues on …

… Deep learning techniques have shown great potential in image … of deep learning architectures
targeting mobile devices like … disease which might run on mobile devices is proposed. …

… This upsurge of mobile devices, applications and services has raised important cybersecurity
challenges due to the exponential increase of attacks and their sophistication [2], [3]. On …

… learning, based on manuallyand expert-originated features, outdated. For these reasons, we
suggest Deep Learning … extracted features, reflecting the complex mobile-traffic patterns. To …

… In practice, deep learning model inference can be offloaded to the cloud or executed on
mobile devices. The cloud-based deep learning model requires mobile devices to send data to …

… localization platform on mobile devices. Additionally, data security has become
increasingly important, especially in medical applications on mobile devices. Deep learning-based …