In recent years, continuous growing interests have been seen in bringing artificial intelligence capabilities to mobile devices. However, the related work still faces several issues, such as constrained computation and memory resources, power drain, and thermal limitation. To develop deep learning (DL) algorithms on mobile devices, we need to understand their behaviors. In this article, we explore the architectural behaviors of some mainstream DL frameworks on mobile devices by performing a comprehensive characterization of performance, accuracy, energy efficiency, and thermal behaviors. We experimentally choose four model compression methods to perform on networks and in addition, analyze the related impact on the nodes amount, memory, execution time, model size, inference time, energy consumption, and thermal distribution. With insights into DL-based mobile application characteristics, we hope to guide the design of future smartphone platforms for lower energy consumption.

Recently, mobile applications have gradually become performance- and resource- intensive, which results in a massive battery power drain and high surface temperature, and further degrades the user experience. Thus, high power consumption and surface over-heating have been considered as a severe challenge to smartphone design. In this paper, we propose DTEHR, a mobile Dynamic Thermal Energy Harvesting Reusing framework to tackle this challenge. The approach is sustainable in that it generates energy using dynamic Thermoelectric Generators (TEGs). The generated energy not only powers Thermoelectric Coolers (TECs) for cooling down hot-spots, but also recharges micro-supercapacitors (MSCs) for extended smartphone usage. To analyze thermal characteristics and evaluate DTEHR across real-world applications, we build MPPTAT (Multi-comPonent Power and Thermal Analysis Tool), a power and thermal analyzing tool for Android. The result shows that DTEHR reduces the temperature differences between hot areas and cold areas up to 15.4°C (internal) and 7°C (surface). With TEC-based hot-spots cooling, DTEHR reduces the temperature of the surface and internal hot-spots by an average of 8° and 12.8mW respectively. With dynamic TEGs, DTEHR generates 2.7-15mW power, more than hundreds of times of power that TECs need to cool down hot-spots. Thus, extra-generated power can be stored into MSCs to prolong battery life.

Image denoising and magnification play an important role in most visual applications such as visual material examination for public security and image-based medical diagnosis. We propose a 1-D kernel fitting algorithm for denoising in space domain and wavelet transformed (WT) domain, and for magnification in space domain. In the algorithm, the values of a column or a row from an image or its transformed version are taken as the measured results of a fitting function. The fitting coefficients are estimated by least square (LS) method. An image is denoised or magnified by resampling the fitted function, or followed by inverse transform if fitting is carried out in a transformed domain. We also discuss a modified singular value decomposition (SVD) method for comparison. To illustrate the application feasibility, the presented methods are experimentally compared with the basic wavelet-thresholding algorithm for image denoising, and with the standard bicubic interpolation method for magnification.

In this letter, we present a new formulation for uncorrelated discriminant analysis (UDA) in some high-dimensional feature space and then propose an efficient UDA algorithm using kernel technique. Unlike some existing UDA algorithms, which solve uncorrelated discriminant vectors one at a time, the proposed algorithm is able to extract all the uncorrelated discriminant vectors simultaneously in the feature space and does not suffer the small sample size problem. Experimental results show that the proposed method is very competitive in comparison with some existing discriminant analysis algorithms, in terms of recognition rate and robustness with respect to kernel parameters.