Information technology can improve the quality, efficiency, and cost of healthcare. In this survey, we examine the privacy requirements of mobile computing technologies that have the potential to transform healthcare. Such mHealth technology enables physicians to remotely monitor patients' health and enables individuals to manage their own health more easily. Despite these advantages, privacy is essential for any personal monitoring technology. Through an extensive survey of the literature, we develop a conceptual privacy framework for mHealth, itemize the privacy properties needed in mHealth systems, and discuss the technologies that could support privacy-sensitive mHealth systems. We end with a list of open research questions.

Convolution layers are prevalent in many classes of deep neural networks, including Convolutional Neural Networks (CNNs) which provide state-of-the-art results for tasks like image recognition, neural machine translation and speech recognition. The computationally expensive nature of a convolution operation has led to the proliferation of implementations including matrix-matrix multiplication formulation, and direct convolution primarily targeting GPUs. In this paper, we introduce direct convolution kernels for x86 architectures, in particular for Xeon and Xeon Phi systems, which are implemented via a dynamic compilation approach. Our JIT-based implementation shows close to theoretical peak performance, depending on the setting and the CPU architecture at hand. We additionally demonstrate how these JIT-optimized kernels can be integrated into a lightweight multi-node graph execution model. This illustrates that single-and multi-node runs yield high efficiencies and high imagethroughputs when executing state-of-the-art image recognition tasks on CPUs.

The Semantic Web is well recognized as an effective infrastructure to enhance visibility of knowledge on the Web. The core of the Semantic Web is ontology, which is used to explicitly represent our conceptualizations. Ontology engineering in the Semantic Web is primarily supported by languages such as RDF, RDFS and OWL. This chapter discusses the requirements of ontologies in the context of the Web, compares the above three languages with existing knowledge representation formalisms, and surveys tools for managing and applying ontologies. Advantages of using ontologies in both knowledge-base-style and database-style applications are demonstrated using three real world applications.

No abstract

No abstract

This paper presents the first comprehensive empirical study demonstrating the efficacy of the Brain Floating Point (BFLOAT16) half-precision format for Deep Learning training across image classification, speech recognition, language modeling, generative networks and industrial recommendation systems. BFLOAT16 is attractive for Deep Learning training for two reasons: the range of values it can represent is the same as that of IEEE 754 floating-point format (FP32) and conversion to/from FP32 is simple. Maintaining the same range as FP32 is important to ensure that no hyper-parameter tuning is required for convergence; e.g., IEEE 754 compliant half-precision floating point (FP16) requires hyper-parameter tuning. In this paper, we discuss the flow of tensors and various key operations in mixed precision training, and delve into details of operations, such as the rounding modes for converting FP32 tensors to BFLOAT16. We have implemented a method to emulate BFLOAT16 operations in Tensorflow, Caffe2, IntelCaffe, and Neon for our experiments. Our results show that deep learning training using BFLOAT16 tensors achieves the same state-of-the-art (SOTA) results across domains as FP32 tensors in the same number of iterations and with no changes to hyper-parameters.

A wireless sensor network deployed in an area of interest is affected by variations in environmental conditions associated with that area. It must adapt to these variations in order to continue functioning as desired by the user. We present a novel, two-phase solution to the wireless sensor network adaptivity problem. In the first phase, nodes in the network, organized as clusters, execute an efficient algorithm to dynamically calibrate sensed data. Each node provides its current energy level and the state of each on-board sensor to a cluster-head. In the second phase, each clusterhead executes an efficient, ontology-driven algorithm to determine the future state of the network under existing conditions, based on information received from each sensor node. We describe an example application scenario to show how our two-phase solution can be employed to enable a realworld wireless sensor network to adapt itself to variations in environmental conditions.

No abstract