Convolutional Neural Networks (CNN) continue to dominate research in the area of hardware acceleration using Field Programmable Gate Arrays (FPGA), proving its effectiveness in a variety of computer vision applications such as object segmentation, image classification, face detection, and traffic signs recognition, among others. However, there are numerous constraints for deploying CNNs on FPGA, including limited on-chip memory, CNN size, and configuration parameters. This paper introduces Ad-MobileNet, an advanced CNN model inspired by the baseline MobileNet model. The proposed model uses an Ad-depth engine, which is an improved version of the depth-wise separable convolution unit. Moreover, we propose an FPGA-based implementation model that supports the Mish, TanhExp, and ReLU activation functions. The experimental results using the CIFAR-10 dataset show that our Ad-MobileNet has a classification accuracy of 88.76% while requiring little computational hardware resources. Compared to state-of-the-art methods, our proposed method has a fairly high recognition rate while using fewer computational hardware resources. Indeed, the proposed model helps to reduce hardware resources by more than 41% compared to that of the baseline model.
Deep Learning techniques have been successfully applied to solve many Artificial Intelligence (AI) applications problems. However, owing to topologies with many hidden layers, Deep Neural Networks (DNNs) have high computational complexity, which makes their deployment difficult in contexts highly constrained by requirements such as performance, real-time processing, or energy efficiency. Numerous hardware/software optimization techniques using GPUs, ASICs, and reconfigurable computing (i.e, FPGAs), have been proposed in the literature. With FPGAs, very specialized architectures have been developed to provide an optimal balance between high-speed and low power. However, when targeting edge computing, user requirements and hardware constraints must be efficiently met. Therefore, in this work, we only focus on reconfigurable embedded systems based on the Xilinx ZYNQ SoC and popular DNNs that can be implemented on Embedded Edge improving performance per watt while maintaining accuracy. In this context, we propose an automated framework for the implementation of hardware-accelerated DNN architectures. This framework provides an end-to-end solution that facilitates the efficient deployment of topologies on FPGAs by combining custom hardware scalability with optimization strategies. Cutting-edge comparisons and experimental results demonstrate that the architectures developed by our framework offer the best compromise between performance, energy consumption, and system costs. For instance, the low power (0.266W) DNN topologies generated for the MNIST database achieved a high throughput of 3,626 FPS.
We need open platforms driven by specialists, in which queries can be created and collected for long periods and the diagnosis made based on a rigorous clinical follow-up. In this work, we developed a multi-language robot interface helping to evaluate the mental health of seniors by interacting through questions. Through the voice interface, the specialist can propose questions, as well as receive users’ answers, in text form. The robot can automatically interact with the user using the appropriate language. It can process the answers and under the guidance of a specialist, questions and answers can be oriented towards the desired therapy direction. The prototype was implemented on an embedded device meant for edge computing, thus it was able to filter environmental noise and can be placed anywhere at home. The proposed platform allows the integration of well-known open source and commercial data flow processing frameworks. The experience is now available for specialists to create queries and answers through a Web-based interface.
Nowadays, the development of the Fast Fourier Transform (FFT) remains of a great importance due to its substantial role in the field of signal processing and imagery. This latter still attracts the attention of several researchers around the globe. In this paper, an optimized design of the FFT using the radix-2 algorithm, 32 point is proposed. The developed architecture was implemented using an FPGA regarding its flexibility as well as its parallelism and its computational speed. Though, the material resources of the FPGA are limited, particularly the integrated DSP blocks, a new calculation approach was introduced during the VHDL description with the aim to reduce the necessary number of multiplication operation. The experimental validation of the adopted architecture was realized using a Virtex 6, where the numerical synthesis and the post and route described in VHDL was realized using ISE Design Suite 14.7.
Nowadays, Deep Learning DL becoming more and more interesting in many areas, such as genomics, security, data analysis, image, and video processing. However, DL requires more and more powerful and parallel computing. The calculation performed by super-machines equipped with powerful processors, such as the latest GPUs. Despite their power, these computing units consume a lot of energy, which makes their use very difficult in small embedded systems and edge computing. To overcome the problem for which we must keep the maximum performance and satisfy the power constraint, it is necessary to use a heterogeneous strategy. Some solutions are promising when using less energyconsuming electronic circuits, such as FPGAs associated with less expensive topologies such as Stacked Sparse Autoencoders. Our target architecture is the Xilinx ZYNQ 7020 SoC, which combines a dual-core ARM processor and an FPGA in the same chip. In the interest of flexibility, we decided to leverage the performance of Xilinx’s high-level synthesis tools, evaluate and choose the best solution in terms of size and performance of the data exchange, synchronization and pipeline processing. The results show that our implementation gives high performance at very low energy consumption. Indeed, the evaluation of our accelerator shows that it can classify 1160 MNIST images per second, consuming only 0.443 W; 2.4 W for the entire system. More than the low energy consumption and the high performance, the platform used only costs $ 125.
Deep Neural Networks (DNNs) deployment for IoT Edge applications requires strong skills in hardware and software. In this paper, a novel design framework fully automated for Edge applications is proposed to perform such a deployment on System-on-Chips. Based on a high-level Python interface that mimics the leading Deep Learning software frameworks, it offers an easy way to implement a hardware-accelerated DNN on an FPGA. To do this, our design methodology covers the three main phases: (a) customization: where the user specifies the optimizations needed on each DNN layer, (b) generation: the framework generates on the Cloud the necessary binaries for both FPGA and software parts, and (c) deployment: the SoC on the Edge receives the resulting files serving to program the FPGA and related Python libraries for user applications. Among the study cases, an optimized DNN for the MNIST database can speed up more than 60× a software version on the ZYNQ 7020 SoC and still consume less than . A comparison with the state-of-the-art frameworks demonstrates that our methodology offers the best trade-off between throughput, power consumption, and system cost.