More Like this

1. High Impulse Noise Intensity Removal in Natural Images Using Convolutional Neural Network

   https://doi.org/10.1109/CCWC47524.2020.9031200  

   Mafi, Mehdi; Izquierdo, Walter; Adjouadi, Malek (January 2020, IEEE 10th Annual Computing and Communication Workshop and Conference (CCWC))

   This paper introduces a new image smoothing filter based on a feed-forward convolutional neural network (CNN) in presence of impulse noise. This smoothing filter integrates a very deep architecture, a regularization method, and a batch normalization process. This fully integrated approach yields an effectively denoised and smoothed image yielding a high similarity measure with the original noise free image. Specific structural metrics are used to assess the denoising process and how effective was the removal of the impulse noise. This CNN model can also deal with other noise levels not seen during the training phase. The proposed CNN model is constructed through a 20-layer network using 400 images from the Berkeley Segmentation Dataset (BSD) in the training phase. Results are obtained using the standard testing set of 8 natural images not seen in the training phase. The merits of this proposed method are weighed in terms of high similarity measure and structural metrics that conform to the original image and compare favorably to the different results obtained using state-of-art denoising filters. 

   more » « less
2. A Neuromorphic Sparse Coding Defense to Adversarial Images

   https://doi.org/10.1145/3354265.3354277  

   Kim, Edward; Yarnall, Jessica; Shah, Priya; Kenyon, Garrett T. (July 2019, ICONS '19: Proceedings of the International Conference on Neuromorphic Systems)

   Adversarial images are a class of images that have been slightly altered by very specific noise to change the way a deep learning neural network classifies the image. In many cases, this particular noise is imperceptible to the human vision system and thus presents a vulnerability of significant concern to the machine learning and artificial intelligence community. Research towards mitigating this type of attack has taken many forms, one of which is to filter or post process the image before classifying the image with a deep neural network. Techniques such as smoothing, filtering, and compression have been used with varying levels of success. In our work, we explored the use of a neuromorphic software and hardware approach as a protection against adversarial image attack. The algorithm governing our neuromorphic approach is based upon sparse coding. Our sparse coding approach is solved using a dynamic system of equations that models biological low level vision. Our quantitative and qualitative results show that a sparse coding reconstruction is remarkably invariant to changes in sparsity and reconstruction error with respect to classification accuracy. Furthermore, our approach is able to maintain low reconstruction errors without sacrificing classification performance. 

   more » « less
3. A van der Waals interfacial junction transistor for reconfigurable fuzzy logic hardware

   https://doi.org/10.1038/s41928-024-01256-3  

   Liu, Hefei; Wu, Jiangbin; Ma, Jiahui; Yan, Xiaodong; Yang, Ning; He, Xu; He, Yangu; Zhang, Hongming; Hsu, Ting-Hao; Qian, Justin H; et al (October 2024, Nature Electronics)

   Edge devices face challenges when implementing deep neural networks due to constraints on their computational resources and power consumption. Fuzzy logic systems can potentially provide more efficient edge implementations due to their compactness and capacity to manage uncertain data. However, their hardware realization remains difficult, primarily because implementing reconfigurable membership function generators using conventional technologies requires high circuit complexity and power consumption. Here we report a multigate van der Waals interfacial junction transistor based on a molybdenum disulfide/graphene heterostructure that can generate tunable Gaussian-like and π-shaped membership functions. By integrating these generators with peripheral circuits, we create a reconfigurable fuzzy controller hardware capable of nonlinear system control. This fuzzy logic system can also be integrated with a few-layer convolution neural network to form a fuzzy neural network with enhanced performance in image segmentation. 

   more » « less
4. Keep Clear of the Edges : An Empirical Study of Artificial Intelligence Workload Performance and Resource Footprint on Edge Devices

   https://doi.org/10.1109/IPCCC55026.2022.9894338  

   Suo, Kun; Nguyen, Tu N.; Shi, Yong; He, Jing Selena; Hung, Chih-Cheng (November 2022, 2022 IEEE International Performance, Computing, and Communications Conference (IPCCC))

   Recently, with the advent of the Internet of everything and 5G network, the amount of data generated by various edge scenarios such as autonomous vehicles, smart industry, 4K/8K, virtual reality (VR), augmented reality (AR), etc., has greatly exploded. All these trends significantly brought real-time, hardware dependence, low power consumption, and security requirements to the facilities, and rapidly popularized edge computing. Meanwhile, artificial intelligence (AI) workloads also changed the computing paradigm from cloud services to mobile applications dramatically. Different from wide deployment and sufficient study of AI in the cloud or mobile platforms, AI workload performance and their resource impact on edges have not been well understood yet. There lacks an in-depth analysis and comparison of their advantages, limitations, performance, and resource consumptions in an edge environment. In this paper, we perform a comprehensive study of representative AI workloads on edge platforms. We first conduct a summary of modern edge hardware and popular AI workloads. Then we quantitatively evaluate three categories (i.e., classification, image-to-image, and segmentation) of the most popular and widely used AI applications in realistic edge environments based on Raspberry Pi, Nvidia TX2, etc. We find that interaction between hardware and neural network models incurs non-negligible impact and overhead on AI workloads at edges. Our experiments show that performance variation and difference in resource footprint limit availability of certain types of workloads and their algorithms for edge platforms, and users need to select appropriate workload, model, and algorithm based on requirements and characteristics of edge environments. 

   more » « less
5. Acoustic and flow measurements of porous plate designs for aerodynamic noise mitigation

   Kershner, John R (August 2024, Lehigh University)

   An experimental study investigates parametrically the effects of porosity on the acoustic and aerodynamic fields about lifting- and non-lifting surfaces at two separate aeroacoustic facilities using microphone arrays and hot-wire anemometry. A single dimensionless porosity parameter characterizes the flow noise generated by a turbulent boundary layer and informs the design of the porous edge test specimens, including perforated flat plates and flat-plate extensions with a blunt or sharp trailing edge. The strong tonal peak due to vortex shedding from blunt trailing-edges diminishes in magnitude as the porosity parameter increases, and high-porosity plates eliminate this tone from the acoustic spectra. Single-microphone measurements indicate further that the porous plates examined can reduce low-frequency noise and increase high-frequency excess noise levels by up to 10 dB. DAMAS beamforming of the porous plates with sharpened edges reveal similar results on the acoustic spectra and identify that the principal effect of edge porosity on the acoustic source regions is a reduction in low-frequency noise and an increase in high-frequency noise across the entire plate. Noise generated by porous edges in the low-frequency range by the trailing- and leading-edge regions can be reduced by up to 20 dB, and porous edges increase high-frequency noise by up to 20 dB. Plates with the same dimensionless porosity perform similarly, where plates with circular holes perform slightly better (2 dB) than their counterparts with square holes at reducing low-frequency noise the most and increasing high-frequency noise the least in wind tunnel testing. Hot-wire anemometry of the flow field about blunt porous trailing edges reveals a downward shift of the bluntness-induced vortex-shedding peak in the spectra of turbulent velocity fluctuations, which are not seen in the acoustic spectra. In addition, flow field measurements for both the blunt-edged and sharp-edge plates indicate significant increases in turbulence intensity at the plate surface which are believed to be caused by the presence of holes and related to the increase in noise seen at high frequencies. The wing of a remote-controlled glider is modified with porous plates near the trailing edge to demonstrate reductions in surface pressure level fluctuations on a flying vehicle at the owl scale. Measurements of these fluctuations on the wing and fuselage indicate the capacity of porous plates to modestly reduce surface pressure levels in select frequency ranges and settings of aerial vehicles. 

   more » « less