The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Background Modelling is a crucial step in background/foreground detection which could be used in video analysis, such as surveillance, people counting, face detection and pose estimation. Most methods need to choose the hyper parameters manually or use ground truth background masks (GT). In this work, we present an unsupervised deep background (BG) modelling method called BM-Unet which is based on...
Consider the problem of energy loss caused by inefficient use of energy in Wireless Sensor Networks (WSN). A clustering energy-efficient transmission protocol for wireless sensor networks based on ant colony path optimization (CEETP-ACPO) is proposed. Firstly, use the distributed cluster computing energy-efficient routing scheme (DCCERS) to select cluster heads according to the center of gravity and...
A method based on variable horizon predictive control is proposed in the paper for nominal trajectory guidance. Firstly, a feasible reference trajectory is generated by the Gauss pseudospectral method. Then, curvature is employed to represent the smoothness of obtained trajectory and predictive horizon is selected according to the curvature. Different predictive control optimal problems are established...
In order to save energy and improve the driving distance of electric vehicle, a regenerative braking control strategy based on fuzzy control for the electric vehicle with four in-wheel motors is proposed in this paper. Firstly, the braking force is distributed between front axis and rear axis to ensure the safety and stability of the vehicle. Secondly, the braking force is distributed between hydraulic...
Thanks to the ubiquitous computing, the scale of data collection in various fields has been growing rapidly. Medicine is one of the fields that can benefit from the big data. However, it is faced with a big challenge because medical datasets are normally in high dimensions. Therefore, reducing dimensionality and finding the optimal set of features or attributes is of great importance. This paper presents...
Activity recognition is mainly used in health care, authentication and many other fields. Activity recognition based on a smart watch usually performs much better than any other means of activity recognition in these areas. With its small size, high integration and multi-function, smart watch holds more advantages over the devices used in image based activity recognition, for example, a monitor, which...
Container, as a light-weight virtualization solution, emerges in recent years, and provides effective approaches for managing computing resources. Due to the complexity of the containerized computing environment, setting up runtime configuration presents a great challenge. To make better use of hardware resources and simplify the processes of environment setup, we propose a resource provisioning approach...
On functional requirements of atmospheric particle monitoring system, this paper designs a distributed atmospheric particle monitoring system. The proposed system consists of a data acquisition network, embedded gateways, a database server and remote monitoring terminals. The data acquisition network consists of mobile data acquisition nodes and router nodes distributed in monitoring areas which are...
Cloud computing and virtualization technologies play important roles in modern service-oriented computing paradigm. More conventional services are being migrated to virtualized computing environments to achieve flexible deployment and high availability. We introduce a schedule algorithm based on fuzzy inference system (FIS), for global container resource allocation by evaluating nodes' statuses using...
Rapidly growing data volume demand systems that have the ability to handle massive heterogeneous unstructured data sets in digital home environment. However, currently, most existing mature transaction processing systems are built upon relational databases with structured data. In this paper, we design a hybrid development framework, to offer greater scalability and flexibility of data analysis and...
In this paper, we propose a novel approach based on deep belief networks for features learning of ECG arrhythmias. The method consists of four steps: ECG signals preprocessing, segmentation and resampling, features learning, and validation. In the resampling stage all segmented ECG beats are changed into the same periodic length for the deep learning model. For extracting features of ECG data, we...
With the development of the teaching and research of big data processing and distributed algorithms, there emerges an increasing need to leverage low-cost hardware to build the distributed computing test environment for the purpose of the algorithm validation and experiment simulation. In this paper, we propose a distributed computing testbed using the affordable Raspberry Pi board as the basic computing...
There emerges an increasing need to mine and analyze the health data from smart home medical systems and community medical organizations. Regarding to the influence of irrelevant attributes, in this study, an improved C4.5 decision tree method based on RELIEFF attribute weighting techniques is proposed for medical diagnosis. This method includes two steps: the first step is to delete the irrelevant...
Many crowd abnormal motion detection methods in video surveillance have been proposed in resent years. However, most of them are based on low semantic features, such gray value, velocity and gradient. Usually, low semantic features contain weak discriminative information of the scene. In addition, these methods often ignore important information in time and space dimension. In this work, a high semantic...
This paper proposes a distributed control system for flexible loads using a recommendation mechanism. The recommendation mechanism is implemented at the aggregator level and coordinates the flexible loads through smart controllers based on a ranking algorithm. In the existing demand response system, the aggregator broadcasts control sequences to flexible loads and collect schedules from them. The...
Screen printing is a low cost and highly efficient printing technology. Its application to the fabrication of RF antennas is introduced in this study. Applications of screen printed antennas for RHU, frequency selective surfaces and energy harvesting applications are presented.
Position-based Routing Vehicular Ad-hoc Network (PBR-VANET) is a specific type of mobile Ad-hoc network where the nodes are present as vehicles and the routing is decided based on node position. However, PBR-VANET routing protocols greatly suffer from mass packet loss due to frequent changes in topology. We discuss the requirements of the routing protocol and propose a routing encapsulation protocol...
A fast algorithm is presented for time-domain statistical analysis of large circuits with multiple stochastic parameters. The proposed technique is based on Numerical Inversion of Laplace Transform and does not require explicit presentation of the dynamic model in the form of set of differential equations. As a result, the moment vectors associated with frequency can be excluded when forming the moments...
The non-ideal factors of permanent magnet synchronous motor (PMSM) drive system, such as harmonics of rotor flux, cogging torque, and voltage source inverter (VSI) nonlinearity cause the speed ripple and deteriorate the speed and current regulation performance. To suppress these disturbances, this paper proposes a novel cascaded robust current and speed control stragety for PMSM. The proposed method...
A fast algorithm is presented for statistical analysis of large microwave and high-speed circuits with multiple stochastic parameters. Using the proposed algorithm, a set of local reduced-order parameterized circuits are derived based on adaptive frequency sampling and implicit multi-moment matching projection techniques. The local models preserve the stochastic parameters as symbolic quantities....
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.