دانلود و نمایش مقالات مرتبط با Embedded platform::صفحه 1
بلافاصله پس از پرداخت دانلود کنید

با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد). 

نتیجه جستجو - Embedded platform

تعداد مقالات یافته شده: 5
ردیف عنوان نوع
1 063-S0893608020304470
063-S0893608020304470-2021
Deep Neural Networks (DNNs) have become popular for various applications in the domain of image and computer vision due to their well-established performance attributes. DNN algorithms involve powerful multilevel feature extractions resulting in an extensive range of parameters and memory footprints. However, memory bandwidth requirements, memory footprint and the associated power consumption of models are issues to be addressed to deploy DNN models on embedded platforms for real time vision-based applications. We present an optimized DNN model for memory and accuracy for vision-based applications on embedded platforms. In this paper we propose Quantization Friendly MobileNet (QF-MobileNet) architecture. The architecture is optimized for inference accuracy and reduced resource utilization. The optimization is obtained by addressing the redundancy and quantization loss of the existing baseline MobileNet architectures. We verify and validate the per- formance of the QF-MobileNet architecture for image classification task on the ImageNet dataset. The proposed model is tested for inference accuracy and resource utilization and compared to the baseline MobileNet architecture. The inference accuracy of the proposed QF-MobileNetV2 float model attained 73.36% and the quantized model has 69.51%. The MobileNetV3 float model attained an inference accuracy of 68.75% and the quantized model has 67.5% respectively. The proposed model saves 33% of time complexity for QF-MobileNetV2 and QF-MobileNetV3 models against the baseline models. The QF-MobileNet also showed optimized resource utilization with 32% fewer tunable parameters, 30% fewer MAC’s operations per image and reduced inference quantization loss by approximately 5% compared to the baseline models. The model is ported onto the android application using TensorFlow API. The android application performs inference on the native devices viz. smartphones, tablets and handheld devices. Future work is focused on introducing channel-wise and layer-wise quantization schemes to the proposed model. We intend to explore quantization aware training of DNN algorithms to achieve optimized resource utilization and inference accuracy.© 2020 Elsevier Ltd. All rights reserved.
Keywords: Deep Neural Network | Classification | MobileNet | Computer vision | Embedded platform | Quantization
مقاله انگلیسی
2 Benchmarking vision kernels and neural network inference accelerators on embedded platforms
محک زدن هسته بینایی و شتاب دهنده های استنتاج شبکه عصبی بر روی سیستم عامل های توکار-2021
Developing efficient embedded vision applications requires exploring various algorithmic optimization trade- offs and a broad spectrum of hardware architecture choices. This makes navigating the solution space and finding the design points with optimal performance trade-offs a challenge for developers. To help provide a fair baseline comparison, we conducted comprehensive benchmarks of accuracy, run-time, and energy efficiency of a wide range of vision kernels and neural networks on multiple embedded platforms: ARM57 CPU, Nvidia Jetson TX2 GPU and Xilinx ZCU102 FPGA. Each platform utilizes their optimized libraries for vision kernels (OpenCV, Vision Works and xfOpenCV) and neural networks (OpenCV DNN, TensorRT and Xilinx DPU). Forvision kernels, our results show that the GPU achieves an energy/frame reduction ratio of 1.1–3.2× compared to the others for simple kernels. However, for more complicated kernels and complete vision pipelines, the FPGA outperforms the others with energy/frame reduction ratios of 1.2–22.3×. For neural networks [Inception-v2 and ResNet-50, ResNet-18, Mobilenet-v2 and SqueezeNet], it shows that the FPGA achieves a speed up of [2.5, 2.1, 2.6, 2.9 and 2.5]× and an EDP reduction ratio of [1.5, 1.1, 1.4, 2.4 and 1.7]× compared to the GPU FP16 implementations, respectively.
Keywords: Benchmarks | CPUs | GPUs | FPGAs | Embedded vision | Neural networks
مقاله انگلیسی
3 Optimized hardware accelerators for data mining applications on embedded platforms: Case study principal component analysis
شتاب دهنده سخت افزاری بهینه سازی شده برای برنامه های استخراج داده بر روی چهارچوب های embedded: مطالعه موردی تجزیه و تحلیل مؤلفه اصلی-2019
With the proliferation of mobile, handheld, and embedded devices, many applications such as data min- ing applications have found their way into these devices. However, mobile devices have stringent area and power limitations, high speed-performance, reduced cost, and time-to-market requirements. Furthermore, applications running on mobile devices are becoming more complex requiring high processing power. These design constraints pose serious challenges to the embedded system designers. In order to pro- cess the applications on mobile and embedded systems, effectively and efficiently, optimized hardware architectures are needed. We are investigating the utilization of FPGA-based customized hardware to ac- celerate embedded data mining applications including handwritten analysis and facial recognition. For these biometric applications, Principal Component Analysis (PCA) is applied initially, followed by similar- ity measure. In this research work, we introduce novel and efficient embedded hardware architectures to accelerate the PCA computation. PCA is a classic technique to reduce the dimensionality of data by transforming the original data set into a new set of variables called Principal Components (PCs) that rep- resent the key features of the data. We propose two hardware versions for PCA computation, each with its unique optimization techniques to enhance the performance of our designs, and one specifically with additional techniques to reduce the memory access latency of embedded platforms. To the best of our knowledge, we could not find similar work for PCA, specifically catered to the embedded devices, in the published literature. We perform experiments to evaluate the feasibility and efficiency of our designs us- ing a benchmark dataset for biometrics. Our embedded hardware designs are generic, parameterized, and scalable; and achieve 78 times speedup as compared to its software counterparts
Keywords: Data mining | Dimensionality reduction techniques | Embedded and mobile systems | FPGAs | Hardware acceleration | Principal Component Analysis
مقاله انگلیسی
4 Dynamic security management for real-time embedded applications in industrial networks
مدیریت امنیت پویا برای برنامه های تعبیه شده زمان واقعی در شبکه های صنعتی-2015
Widely deployed real-time embedded systems can improve the performance of industrial applications, but these systems also face the critical challenge of providing high quality security in an unpredictable network environment. We measure the time and energy consumptions of commonly used cryptographic algorithms on a real embedded platform and introduce a method to quantify the security risk of real-time applications. We propose a Dynamic Security Risk Management (DSRM) mechanism to manage the aperiodic real-time tasks for networked industrial applications. Inspired by the feedback design philosophy, DSRM is designed as a two-level control mechanism. The upper-level component makes efforts to admit or reject the arrival tasks and assigns the reasonable security level for each admitted task. With three proportional feedback controllers at the lower level, the security level of each ready task can be adjusted adaptively according to the dynamic environments. Simulation results show the superiority of the proposed mechanism. Keywords: Real-time embedded system Security management Risk Feedback control Scheduling
مقاله انگلیسی
5 Real Time Copyright Protection and Implementation of Image and Video Processing on Android and Embedded Platforms
حفاظت کپی رایت زمان واقعی و پیاده سازی پردازش تصویر و ویدئو در آندروید و سیستم عامل های جاسازی شده-2015
In this paper, we have proposed real time copyright protection algorithm using both visible as well as invisible watermarking schemes and also implementation of real time image and video processing techniques on Android and Embedded Platform for privacy prevention. We propose invisible watermarking using DCT analysis. Visible watermarking is implemented using image processing properties of Android. We also implement real-time video processing like Canny Edge Detection, Dilation, and Successive frame subtraction on Android and embedded platforms. In this system, pre-specified copyright information is embedded directly on pictures when they are taken. These techniques were also implemented on Beagle board-xM. Keywords: Android | Digital Watermarking | OpenCV | Discrete Cosine Transform (DCT) | Beagleboard-xM | Smartphone
مقاله انگلیسی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی
logo-samandehi
بازدید امروز: 1707 :::::::: بازدید دیروز: 0 :::::::: بازدید کل: 1707 :::::::: افراد آنلاین: 75