No abstract

Breakthroughs from the field of deep learning are radically changing how sensor data are interpreted to extract the high-level information needed by mobile apps. It is critical that the gains in inference accuracy that deep models afford become embedded in future generations of mobile apps. In this work, we present the design and implementation of DeepX, a software accelerator for deep learning execution. DeepX significantly lowers the device resources (viz. memory, computation, energy) required by deep learning that currently act as a severe bottleneck to mobile adoption. The foundation of DeepX is a pair of resource control algorithms, designed for the inference stage of deep learning, that: (1) decompose monolithic deep model network architectures into unit-blocks of various types, that are then more efficiently executed by heterogeneous local device processors (e.g., GPUs, CPUs); and (2), perform principled resource scaling that adjusts the architecture of deep models to shape the overhead each unit-blocks introduces. Experiments show, DeepX can allow even large-scale deep learning models to execute efficiently on modern mobile processors and significantly outperform existing solutions, such as cloud-based offloading.

Wearables and mobile devices see the world through the lens of half a dozen low-power sensors, such as, barometers, accelerometers, microphones and proximity detectors. But differences between sensors ranging from sampling rates, discrete and continuous data or even the data type itself make principled approaches to integrating these streams challenging. How, for example, is barometric pressure best combined with an audio sample to infer if a user is in a car, plane or bike? Critically for applications, how successfully sensor devices are able to maximize the information contained across these multi-modal sensor streams often dictates the fidelity at which they can track user behaviors and context changes. This paper studies the benefits of adopting deep learning algorithms for interpreting user activity and context as captured by multi-sensor systems. Specifically, we focus on four variations of deep neural networks that are based either on fully-connected Deep Neural Networks (DNNs) or Convolutional Neural Networks (CNNs). Two of these architectures follow conventional deep models by performing feature representation learning from a concatenation of sensor types. This classic approach is contrasted with a promising deep model variant characterized by modality-specific partitions of the architecture to maximize intra-modality learning. Our exploration represents the first time these architectures have been evaluated for multimodal deep learning under wearable data -- and for convolutional layers within this architecture, it represents a novel architecture entirely. Experiments show these generic multimodal neural network models compete well with a rich variety of conventional hand-designed shallow methods (including feature extraction and classifier construction) and task-specific modeling pipelines, across a wide-range of sensor types and inference tasks (four different datasets). Although the training and inference overhead of these multimodal deep approaches is in some cases appreciable, we also demonstrate the feasibility of on-device mobile and wearable execution is not a barrier to adoption. This study is carefully constructed to focus on multimodal aspects of wearable data modeling for deep learning by providing a wide range of empirical observations, which we expect to have considerable value in the community. We summarize our observations into a series of practitioner rules-of-thumb and lessons learned that can guide the usage of multimodal deep learning for activity and context detection.

creates challenges with enormous technical, societal, economic, and political consequences. Consequently, a wide range of researchers from academia and industry, as well as businesses, government agencies, and cities, are exploring this exciting technology from three main perspectives: scientific theory, engineering design, and the user experience.Motivated by this more holistic view, the research community has moved its focus from the system to the end user. This shift aims to empower users by providing them with the knowledge required to understand and control their environment, as well as by offering new accessible and interactive interfaces that go beyond the traditional desktop.With this in mind, this special issue of Computer presents five recent research and deployment case studies. Two of the articles project our readers into futurist scenarios: one imagines nanotechnologies' penetration into embedded computing and electronics, while the other discusses the extent to which neuroscience will drive future IoT development. The remaining three articles offer detailed insight into technological solutions that are unleashing new forms of AI and programming constructs, and discuss their societal impact through end-user empowerment. All of the articles are at the forefront of the user-centered design approach.

No abstract

Detecting and reacting to user behavior and ambient context are core elements of many emerging mobile sensing and Internet-of-Things (IoT) applications. However, extracting accurate inferences from raw sensor data is challenging within the noisy and complex environments where these systems are deployed. Deep Learning-is one of the most promising approaches for overcoming this challenge, and achieving more robust and reliable inference. Techniques developed within this rapidly evolving area of machine learning are now state-of-the-art for many inference tasks (such as, audio sensing and computer vision) commonly needed by IoT and wearable applications. But currently deep learning algorithms are seldom used in mobile/IoT class hardware because they often impose debilitating levels of system overhead (e.g., memory, computation and energy). Efforts to address this barrier to deep learning adoption are slowed by our lack of a systematic understanding of how these algorithms behave at inference time on resource constrained hardware. In this paper, we present the first-albeit preliminary-measurement study of common deep learning models (such as Convolutional Neural Networks and Deep Neural Networks) on representative mobile and embedded platforms. The aim of this investigation is to begin to build knowledge of the performance characteristics, resource requirements and the execution bottlenecks for deep learning models when being used to recognize categories of behavior and context. The results and insights of this study, lay an empirical foundation for the development of optimization methods and execution environments that enable deep learning to be more readily integrated into next-generation IoT, smartphones and wearable systems.

No abstract

No abstract