AUTOMATIC CONTROL AND COMPUTER SCIENCES最新文献

Accurate identification and analysis of semantics is beneficial for processing English texts effectively. This article briefly introduced Word2vec, which was used to extract semantic feature vectors from English texts, and the long short-term memory (LSTM) algorithm, which was used for semantic recognition of English texts. The relevant English comment texts were crawled from the Amazon movie database and used in a simulation experiment. The simulation experiment compared three algorithms: back propagation, recurrent neural network (RNN), and LSTM. The results showed that the LSTM algorithm’s recognition results for the part-of-speech and sentiment inclination of English texts were consistent with the label results. As the length of the English text increased, the recognition accuracy of all three algorithms decreased, and the LSTM algorithm had the smallest decrease. For the same length of English text, the LSTM algorithm had the highest accuracy in identifying part-of-speech and sentiment inclination, followed by the RNN algorithm, and the BP algorithm had the lowest. In terms of recognition time, the LSTM algorithm was the least.

Human activity recognition (HAR) has become a focus of study over the past few years. It is widely used in many fields like health, home safety, security, and energy saving, among others. Research around the health area has evidenced an important increase and a promissory impact on the life quality of a population like the elderly. If we combine sensors and a health condition then we may have a technological solution with methods and techniques that will help us to improve life quality. Smart sensors have become popular. They allow us to monitor data and acquire data in real-time. In HAR, they are used to detect actions and activities like breathing, falling, standing up, or walking. Many commercial solutions use this technology in real-life applications. However, we focused this paper on the Vayaar sensor and the WideFind sensor, two commercial sensors based on ultra-wideband technology, with promising performance, as part of a study developed at the Human Health and Activity Laboratory (H2AL) in the Luleå Tekniska Universitet in Sweden. The study performed a technological and commercial comparison applying machine learning techniques in WEKA for two datasets created with the data gathered from each sensor during an experiment, in which precision and accuracy were analyzed as evaluation parameters of the applied methods. It was identified that random forest (RF) and LogitBoost were the most suitable classifiers to process both WideFind and Vayyar datasets. Random forest had a performance of 85.99% of precision, 85.48% of recall, and 96% of ROC area for the WideFind sensor while LogitBoost had a 69.39% of the performance for precision, 68.89% for recall, and 88.35% of ROC area for the Vayaar sensor.

The present paper considers a service system without the input flow of claims, that is, all claims are present in the queue initially from the beginning. The number of such claims equals Θmax, whereas the number of servers equals k. The time of one service has the Erlang distribution. The paper aims to calculate the time distribution until the completion of all services, as well as the average waiting time of one claim.

In this paper, a fixed-time adaptive fuzzy control scheme is investigated to stabilize a class of uncertain nonlinear systems with full-state constraints. A novel secant barrier Lyapunov function (SBLF) is first constructed to design the controller and obtain the fixed-time stability properties by using the (SBLF) in the design process of back-stepping. The adaptive controller is presented to guarantee that the tracking errors of the system can converge into the neighborhood around the equilibrium point in a fixed time and all the system states can be restricted within the predefined time-varying boundaries. By making use of Lyapunov analysis, we can prove that all the signals in the closed loop system are uniformly ultimately bounded and the output is well driven to follow the desired trajectory. Finally, simulations are given to verify the effectiveness of the method.

This paper presents a study of the prerequisites and the original way of transition from a quasi-monostatic antenna system to a monostatic one as applied to ultrawideband pulsed contact radar subsurface sounding at shallow depths. For this purpose, the joint application of ultrawideband electric “Bow-Tie” and magnetic “Bi-Quad” antennas is investigated. The mutual arrangement proposed in this work allows reducing to zero the distance between the centers of the antennas in the plane orthogonal to the direction of signal emission-reception. The results of full-scale tests with the corresponding processing of the obtained ensembles by the example of probing the human body for the detection and determination of the parameters of biological rhythms and a tree trunk 58 cm in diameter showed satisfactory results for the radar with a central frequency of 1.5 GHz. At the same time, the suppression of the useful signal received due to the application of the described design was only 2.3 dB at an acceptable level of the direct signal, which does not lead to overloading of the radar stroboscopic receiver input.

A two-level multisensor data fusion model is proposed to monitor animal breeding environment. The effectiveness of various sensors is judged by the first level of analysis, and the data are screened by calculating the optimal fusion set. The probability distribution function is calculated using fuzzy membership degree and the final decision is obtained using an improved information fusion approach based on D-S evidence theory by the second level of analysis. Conflict allocation is more reasonable when using the improved D-S and the fusion effect is better. Therefore, the real state of the piggery environment can be obtained based on the fusion result, so as to perform corresponding operations on the field equipment.

This article discusses a methodological approach to building models for assessing the effectiveness of a program (project) for creating or modernizing an information security system in the interests of ensuring the sustainability and competitiveness of a company in the face of increasing threats to the integrity, confidentiality, availability, and reliability of information that is important for its activities. At the same time, the effectiveness of a program (project) is understood as the degree of use of the opportunities allocated for their implementation of material, intangible, and temporary resources to achieve the set goals. When mathematically formalizing a generalized efficiency indicator, it is taken into account that the implementation of technical, technological, organizational, and other elements (events) included in this program (project) is accompanied by the influence of many random factors influencing the achievement of their particular goals. The proposed generalized indicator provides a dominant assessment of the effectiveness of programs (projects) taking into account the risks during their implementation.

This article considers the problem of automating the determination of daily water discharge rates based on continuously measured levels and individual water discharge measurements using discharge curves (DCs), which are the most basic characteristic of river (and floodplain) channel capacity and are widely used in river flow analysis and hydraulic calculations. Conclusions on the optimal analytical representation of the DC and the possibilities of constructing a universal model of hydrometric flow analysis are presented.

An approach is proposed to protect user’s personal data stored on mobile devices running the Android OS, which combines multifactor authentication, secret sharing, visual cryptography, and steganography; and it also uses the built-in security features of the operating system. It ensures the confidentiality of personal data even if both the mobile device and the related remote storage (server) are compromised.

This article proposes an approach to study states of complex industrial networks with adaptive topology based on network motifs: statistically significant subgraphs of a larger graph. The presented analysis concerns the applicability of network motifs to characterizing the system’s performance and for short-, medium-, and long-term forecasting of system states. A smart grid network structure is used as an example: it is represented as a directed graph, in which the most frequent motifs are identified; several scenarios of attacks on network nodes are modeled, and a forecast of the network state is compiled. The results of experimental studies demonstrate the accuracy and consistency of the application of this mathematical tool to the considered problems.