Machine Learning and Embedded Computing in Advanced Driver Assistance Systems (ADAS)

Smart Cognitive IoT Devices Using Multi-Layer Perception Neural Network on Limited Microcontroller

The Internet of Things (IoT) era is mainly dependent on the word “Smart”, such as smart cities, smart homes, and smart cars. This aspect can be achieved through the merging of machine learning algorithms with IoT computing models. By adding the Artificial Intelligence (AI) algorithms to IoT, the result is the Cognitive IoT (CIoT). In the automotive industry, many researchers worked on self-diagnosis systems using deep learning, but most of them performed this process on the cloud due to the hardware limitations of the end-devices, and the devices obtain the decision via the cloud servers. Others worked with simple traditional algorithms of machine learning to solve these limitations of the processing capabilities of the end-devices. In this paper, a self-diagnosis smart device is introduced with fast responses and little overhead using the Multi-Layer Perceptron Neural Network (MLP-NN) as a deep learning technique. The MLP-NN learning stage is performed using a Tensorflow framework to generate an MLP model’s parameters. Then, the MLP-NN model is implemented using these model’s parameters on a low cost end-device such as ARM Cortex-M Series architecture. After implementing the MLP-NN model, the IoT implementation is built to publish the decision results. With the proposed implemented method for the smart device, the output decision based on sensors values can be taken by the IoT node itself without returning to the cloud. For comparison, another solution is proposed for the cloud-based architecture, where the MLP-NN model is implemented on Cloud. The results clarify a successful implemented MLP-NN model for little capabilities end-devices, where the smart device solution has a lower traffic and latency than the cloud-based solution.

A Parallel Convolutional Neural Network for Pedestrian Detection

Pedestrian detection is a crucial task in many vision-based applications, such as video surveillance, human activity analysis and autonomous driving. Recently, most of the existing pedestrian detection frameworks only focus on the detection accuracy or model parameters. However, how to balance the detection accuracy and model parameters, is still an open problem for the practical application of pedestrian detection. In this paper, we propose a parallel, lightweight framework for pedestrian detection, named ParallelNet. ParallelNet consists of four branches, each of them learns different high-level semantic features. We fused them into one feature map as the final feature representation. Subsequently, the Fire module, which includes Squeeze and Expand parts, is employed for reducing the model parameters. Here, we replace some convolution modules in the backbone with Fire modules. Finally, the focal loss is led into the ParallelNet for end-to-end training. Experimental results on the Caltech–Zhang dataset and KITTI dataset show that: Compared with the single-branch network, such as ResNet and SqueezeNet, ParallelNet has improved detection accuracy with fewer model parameters and lower Giga Floating Point Operations (GFLOPs).

Electronics and Its Worldwide Research

The contributions of researchers at a global level in the journal Electronics in the period 2012–2020 are analyzed. The objective of this work is to establish a global vision of the issues published in the Electronic magazine and their importance, advances and developments that have been particularly relevant for subsequent research. The magazine has 15 thematic sections and a general one, with the programming of 385 special issues for 2020–2021. Using the Scopus database and bibliometric techniques, 2310 documents are obtained and distributed in 14 thematic communities. The communities that contribute to the greatest number of works are Power Electronics (20.13%), Embedded Computer Systems (13.59%) and Internet of Things and Machine Learning Systems (8.11%). A study of the publications by authors, affiliations, countries as well as the H index was undertaken. The 7561 authors analyzed are distributed in 87 countries, with China being the country of the majority (2407 authors), followed by South Korea (763 authors). The H-index of most authors (75.89%) ranges from 0 to 9, where the authors with the highest H-Index are from the United States, Denmark, Italy and India. The main publication format is the article (92.16%) and the review (5.84%). The magazine publishes topics in continuous development that will be further investigated and published in the near future in fields as varied as the transport sector, energy systems, the development of new broadband semiconductors, new modulation and control techniques, and more.