this paper provides an analytical review of the subject area, approaches and methods for real-time control systems with application of the machine learning. the review helps to choose approaches to control robotic dev...
详细信息
ISBN:
(纸本)9781665426060
this paper provides an analytical review of the subject area, approaches and methods for real-time control systems with application of the machine learning. the review helps to choose approaches to control robotic devices, methods of artificial intelligence to perform pattern recognition and classification, technologies to design a control system and simulate a robotic device. the design and software implementation stage involved the creation of a structural diagram and description of the selected technologies, training a neural network for recognition and classification of geometric objects, software implementation of control system components. the control system was implemented using the Swift programming language and other technologies, and the configuration and creation of a neural network using the CreateML framework.
In the automotive domain there is a renewed interest for the adoption of fixed priority real-time servers, as a way to implement more efficient reservation mechanisms than TDMAbased methods. In this paper, we take adv...
详细信息
Currently, there exist several open-source computer vision libraries designed for human pose estimation from photos and videos. they are mainly focused on the possibility of detecting individuals in the image and retu...
详细信息
ISBN:
(纸本)9781665426060
Currently, there exist several open-source computer vision libraries designed for human pose estimation from photos and videos. they are mainly focused on the possibility of detecting individuals in the image and returning their skeleton determinants. An often overlooked or underdeveloped functionality is tracking the trajectory of the detected people, which presents a serious problem in the process of design automated video surveillance systems. In this work, the author attempts to develop an algorithm for tracking multiple human poses in real-time, based on simple decision filters. the developed solution is designed to work with keypoints obtained from a selected open-source human poses recognition library. the author reveals details related to the method of processing and analysing obtained keypoints, describes the concept of decision filters and presents the results of the software implementation.
While the rapid development of multi-rotor UAVs brings wide applications, it also brings harm to social life and personal safety due to problems such as “indiscriminate flying” and “black flying”. therefore, there...
详细信息
ISBN:
(纸本)9781665453523
While the rapid development of multi-rotor UAVs brings wide applications, it also brings harm to social life and personal safety due to problems such as “indiscriminate flying” and “black flying”. therefore, there is an urgent need to carry out research work on anti-VAV systems. the most critical technology in the countermeasure system is the real-time detection of the target UAV. the traditional YOLOv3 detection algorithm cannot achieve a balance between real-time performance and detection accuracy on airborne embedded devices with limited computing power. therefore, this paper first improves the end structure of MobileNetV3-Small and replaces the backbone network of the original YOLOv3 with it, which greatly reduces the amount of calculation, but brings about the loss of detection accuracy; Next, an improved receptive field module(RFB+) is added, which strengthens the detection ability of targets in complex backgrounds; Finally, the improved YOLOv3 algorithm is named Air-Borne-YOLOv3. the feasibility and superiority of the improved algorithm are proved by the actual flight test results.
In an online collaboration system such as Wikipedia, edit history is stored as revisions. Topics of articles or categories grow and fade over time, and evolutionary information is retained in its edit history. We cons...
详细信息
this paper presents an embedded system that performs activity recognition in the city. Arduino Due boards with infrared, distance and sound sensors are used to collect data in the city and the activity, profile, and g...
详细信息
this paper presents an embedded system that performs activity recognition in the city. Arduino Due boards with infrared, distance and sound sensors are used to collect data in the city and the activity, profile, and group size recognition performance of different machine learning algorithms (RF, SVM, MLP) are compared. the features were extracted based on fixed-size windows around the observations. We show that it is possible to achieve a high accuracy for binary activity recognition with simple features, and we discuss the optimization of different parameters such as the sensors collection frequency, and the storage buffer size. We highlight the challenges of activity recognition using anonymous sensors in the environment, its possible applications and advantages compared to classical smartphone and wearable based approaches, as well as the improvements that will be made in future versions of this system. this work is a first step towards real-time online activity recognition in smart cities, withthe long-term goal of monitoring and offering extended assistance for semi-autonomous people. (C) 2020 the Authors. Published by Elsevier B.V.
Unlike general systems, hardware and software of embeddedsystems are usually customized for specific purposes and many of them are real-timesystems. Withtime changing, their workloads are also changing rapidly and ...
详细信息
ISBN:
(纸本)9781450375221
Unlike general systems, hardware and software of embeddedsystems are usually customized for specific purposes and many of them are real-timesystems. Withtime changing, their workloads are also changing rapidly and maintaining their software becomes a complicated job. the key is to understand their behaviours so that developers can make changes to them according to the new situations. To trace their runtime behaviours, instrumentation techniques are widely used in general systems. However, applying them on embedded system faces several problems including big size growth rate, long instrumentation time, high runtime overhead, etc. As the hardware performance of embedded system are usually limited, these problems are crucial and cannot be ignored. As far as we know, existing tools can only partly solve all these problems. In this paper, we propose ELSE, an Efficient and Link-time, Static instrumentation tool for embedded system. It supports efficient low-level and high-level instrumentation to collect most runtime information developers want. It does not waste any space during instrumentation thus its size growth rate is very small, which is only about 30% of other existing tools. Its processing time is also orders of magnitude less than other existing tools. We optimize the influence of registers and cache which can further reduce its runtime overhead. Overall, ELSE performs the best compared with other state-of-the-art tools on SPEC 2006 benchmarks.
the proceedings contain 60 papers. the topics discussed include: sensor-embedded linear ball bearing for linear guide way pre-load and straightness monitoring;multi-robot coordination through mobile agent;research of ...
ISBN:
(纸本)9781538646434
the proceedings contain 60 papers. the topics discussed include: sensor-embedded linear ball bearing for linear guide way pre-load and straightness monitoring;multi-robot coordination through mobile agent;research of vehicle parameter and sensor systems necessary to control autonomous vehicles;machine learning approach for predictive maintenance in Industry 4.0;filtering scheme for context-aware fog computing in cyber-physical systems;the sensing technology of applying the acoustic emission sensor to the grinding wheel loading phenomenon;accelerating Viterbi algorithm using custom instruction approach;design, development and experimental evaluation of a vortex actuation system;optimal map-based mode selection and powertrain control for a multi-mode plug-in hybrid electric vehicle;spline-based energy-optimal trajectory planning for functionally redundant robots;simulation analysis and performance evaluation of a vibratory feeder actuated by dielectric elastomers;machine learning-based approaches to analyse and improve the diagnosis of endothelial dysfunction;real-time and robust collaborative robot motion control with Microsoft Kinect® V2;control design of an electro-pneumatic gearbox actuator;modeling and simulation of hybrid electric ships with AC power busa case study;low-power wake-up system based on frequency analysis for environmental Internet of things;and scalability of GPU-processed 3D distance maps for industrial environments.
Identifying new and modified attacks is an important task to ensure the normal operation of computer networks connected to the Internet. Using honeypots and honeynets is one of the effective ways to get information ab...
详细信息
ISBN:
(纸本)9781665426060
Identifying new and modified attacks is an important task to ensure the normal operation of computer networks connected to the Internet. Using honeypots and honeynets is one of the effective ways to get information about attackers and their actions as soon as possible. the paper proposes a method of the determination of attack patterns based on information collected by honeypots. To detect patterns, agglomerative clustering of time series of intruders' activity preprocessed by a convolutional encoder is used, the obtained clustering rand index is 82-84%.
Indoor Positioning systems (IPSs) based on different approaches and technologies have been proposed to support localization and navigation applications in indoor environments. the fair benchmarking and comparison of t...
详细信息
ISBN:
(纸本)9781665404020
Indoor Positioning systems (IPSs) based on different approaches and technologies have been proposed to support localization and navigation applications in indoor environments. the fair benchmarking and comparison of these IPSs is a difficult task since each IPS is usually evaluated in very specific and controlled conditions and using private data sets, not allowing reproducibility and direct comparison between the reported results and other competing solutions. In addition, testing and evaluating an IPS in the real world is difficult and time-consuming, especially when considering evaluation in multiple environments and conditions. To enhance IPS assessment, we propose Dioptra, an open access and user-friendly application to support research, development and evaluation of IPSs through simulation. To the best of our knowledge, Dioptra is the first application specially developed to generate synthetic datasets to promote reproducibility and fair benchmarking between IPSs.
暂无评论