Journal of Intelligent & Fuzzy Systems - Volume 38, issue 2

Authors: Yu, Xiaoqing | Zhang, Zenglin | Chai, Rui

Article Type: Research Article

Abstract: To explore wireless sensor network signal transmission characteristics in through-the-earth communication, this paper focused on wireless network signal transmission attenuation by using 433MHz carrier frequency. Sensor nodes electromagnetic wave transmission characteristics were studied under the condition the different receiving node height, horizontal distance between the transmitting node and the receiving node through the wheat field experiments and computer simulation, the relationship between the received signal strength was established, transmission characteristics of field soil information collection sensor nodes in the soil under four wheat stages were put forwarded. The experiment demonstrated that 8 model goodness of fit R2 of effection …of receiving node high and inter-nodes horizontal distance on RSSI(Received Signal Strength Indicator). Besides, three-dimensional surface of RSSI was built in four wheat growing periods, which the fitting model and goodness of fit of RSSI are obtained, and the model verification was conducted through SPASS software. Validation results showed that the model could better predict the received signal strength at different condition through-the-earth communication. The study can provide the technical support for sensor network node deployment and the establishment of the system in soil information acquisition. Show more

Keywords: Wireless sensor networks, experiments, node high, received signal strength, horizontal distance between nodes

DOI: 10.3233/JIFS-179503

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1401-1410, 2020

Authors: Liyang, Zheng | Xinling, Zhang

Article Type: Research Article

Abstract: The collection stability of traditional systems is low, it is not easy to delete interference data, the access speed is slow, and the error cannot be effectively detected. For this reason, this paper designs a new automatic filing optimization system of financial management information under the background of information technology development. From four aspects of data dynamic collection, data de-duplication, data access control and RAID error detection scheme improvement, the traditional system is optimized. The financial management information is collected through a data collection method that ensures high efficiency and high stability. In the process of accessing, the semantic ontology …is formed, and the access group in the time domain is classified by the support vector machine method to improve the access speed. The repetitive data model is established, and the deduplication processing is realized by the fractional Fourier transform technique combined with the post-processing result of fourth-order cumulant. The limited set of HDD error detection is reset to help with long-term filing of RAID system data. The result is high filing speed and good filing effect, and the conclusion that the design system is highly practical is obtained. Show more

Keywords: Information technology, financial management information, automatic, filing system, optimization

DOI: 10.3233/JIFS-179504

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1411-1422, 2020

Authors: Zheng, Leina | Pan, Tiejun | Liu, Jun | Ming, Guo | Zhang, Mengli | Wang, Jun

Article Type: Research Article

Abstract: Quantitative Trading based on Machine Learning can increase the stock exchanging competitive and further enhance stability in the Chinese financial market, while the Risk to income ratio in the A share sector haven’t been studied well enough so far in the Quantitative Trading. The paper study the risk and opportunity in the Chinese share market over the period 2005–2013 under Hidden Markov Model (HMM) system estimator. And then, the quantitative stock selection strategy based on neural network is studied based on multiple factors of the total market value of the constituent stocks in the SSE 50 Index, the OBV energy …wave, the price-earnings ratio, the Bollinger Bands, the KDJ stochastic index, and the RSI indicators. Back testing obtained the conclusion that the Machine Learning strategy is equally valid for Chinese finical market. By analysing the risk of strategic returns, we can also conclude that the Chinese share market is effective in QuantitativeTrading. Show more

Keywords: Machine learning, quantitative trading, hidden markov, neural network

DOI: 10.3233/JIFS-179505

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1423-1433, 2020

Authors: Pan, Tiejun | Zheng, Leina | Liu, Jun | Guo, Ming | Honghui, Chai | Wang, Jun

Article Type: Research Article

Abstract: At present, the identification of wine is artificial, and it has certain subjectivity. An alternative way that predicting brand based on fusion spectrum combined with Compressive Sampling as a dimensionality reduction technique is proposed in order to achieve the fast, scientific quality evaluation for wine. Successful results have been obtained in the wine identification use Artificial Neural Networks (ANNs) which has the faster speed and precision than typical algorithm. In the end, a multi-spectral information fusion analysis method for wine identification is proposed, which is an efficient solution to the problem of counterfeiting wine.

Keywords: Wine identification, fusion spectrum, compressive sampling, artificial neural network

DOI: 10.3233/JIFS-179506

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1435-1441, 2020

Authors: Tian, Yiming | Wang, Xitai | Geng, Yanli | Liuand, Zuojun | Chen, Lingling

Article Type: Research Article

Abstract: Sensor-based human activity recognition has a wide range of applications including caring the elderly, helping chronic patients, fitness, etc. As a new kind of single-layer feedforward network, extreme learning machine (ELM) has faster training speed and stronger generalization performance, which provides an effective technique for activity recognition. However, due to the random determination of input weights and hidden deviations, the ELM may converge to a local minimum in some cases. Therefore, in order to overcome the shortcomings of ELM and design a reliable and accurate recognition system, this paper proposes a multi-classifier recognition framework which utilizes extreme learning machines optimized …by quantum-behaved particle swarm optimization (QPSO) as the base classifiers. The quantum-behaved particle swarm optimization was used to select the optimal parameters of base ELMs which are trained on different attribute characteristics. The proposed approach is assessed with two inertial sensor data sets. Comparative experiments with other optimization methods indicated that QPSO-ELM has better accuracy performance for inertial sensor-based human activityrecognition. The experiment showed that the proposed ensemble QPSO-ELM recognition method achieves an accuracy of 96.4% for recognizing six activities. Show more

Keywords: Activity recognition, extreme learning machine (ELM), quantum-behaved particle swarm optimization (QPSO), multi-classifier fusion

DOI: 10.3233/JIFS-179507

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1443-1453, 2020

Authors: Zhang, Niankun | Huang, Zhigang | Huang, Peidi | Zhao, Ningshe

Article Type: Research Article

Abstract: In order to master the training state and the characteristics of fighting athletes, it need to obtain a lot of real-time data. By analyzing the characteristics of the test and training process of fighting sports, a defensive and offensive model of sport response test and training is constructed, which is easy to monitor and collect the human fighting sports data, aiming at the special needs for the fast response and data accquisition of sport training. Based on this model, the basic requirements of fast response training and testing system are summed up, and a four-layer architecture design scheme is put …forward by using software engineering technology, which is realized by computer hardware and software technology combined with real-time data acquisition and interface design. Finally, the practical verification is carried out by the application of the system, and the visual expression is given by the graph, and the design and implement can meet the requirement of the task. Show more

Keywords: Data acquisition, fast response, system model, design and implement

DOI: 10.3233/JIFS-179508

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1455-1461, 2020

Authors: Yufeng, Shu | Dali, Zuo | Junhua, Zhang | Junlong, Li | Haoquan, Gan | Tian yu, Chen | Lixing, Luo

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219267 .

DOI: 10.3233/JIFS-179509

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1463-1470, 2020

Authors: Luo, Hongying | Liu, Jun | Li, Xuebin

Article Type: Research Article

Abstract: In this paper, the periodic state of a class of nonlinear hydrodynamic models is studied. This study is applicable to many fields, such as engineering, cybernetics and so on. We use the Runge Kutta algorithm. First, we give a four order nonlinear hydrodynamic model based on the Runge Kutta algorithm. Then, we study the periodic dynamic characteristics of the nonlinear model and establish some new sufficient conditions. The results of our study promote and improve the existing results. And the numerical results are also verified by the numerical experiments. Therefore, the study of this paper has a great help to …master the periodic motion of the fluid. Show more

Keywords: Runge-Kutta algorithm, nonlinear dynamic system, periodic solution, Liapunov function method

DOI: 10.3233/JIFS-179510

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1471-1476, 2020

Authors: Wang, Hailun | Fei, Wu

Article Type: Research Article

Abstract: Compressive sensing retains the substantive characteristics of the original signal based on several sampling values and can realize distortionless reconstruction of signals with high probability. Hence, compressive sensing solves the contradictions among massive sampling data, signal processing speed and hardware equipment in the framework of traditional Shannon’s sampling theorem. In this study, as a means of compressive sensing, a new failure recognition method of rolling bearing based on the characteristic parameters of compressed data and fuzzy-C mean (FCM) clustering is proposed. In this method, kurtosis, variance and waveform factor are used as the characteristic parameters. Using the proposed method, the …sensitive characteristics were extracted by using the compressed information directly, and the eigenvectors of the sample signals were classified and identified through FCM clustering. In the experiment, the proposed method was compared with different compressed matrix methods and the traditional signal acquisition methods under the same axis diameter and different axis diameters. The results demonstrated the improved performance of the proposed method compared to the other methods. Show more

Keywords: Failure recognition, compressive sensing, FCM clustering, characteristic parameters

DOI: 10.3233/JIFS-179511

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1477-1485, 2020

Authors: Wang, Li | Xie, Yuxin | Xu, Jiping | Zhang, Huiyan | Wang, Xiaoyi | Yu, Jiabin | Sun, Qian | Zhao, Zhiyao

Article Type: Research Article

Abstract: The process of cyanobacteria bloom in rivers and lakes is a highly non-stationary and non-linear process. The existing cyanobacterial bloom prediction method mainly uses time series model and single intelligent model, but time series model and single intelligent model cannot effectively explain the cyanobacterial bloom generation process, and the prediction accuracy is not high. In view of the above deficiencies, this paper proposes to use the cyanobacteria bloom spatiotemporal sequence data for modeling. Considering the characteristics of large-scale nonlinear trend term and small-scale residual term in the cyanobacteria bloom spatial-temporal sequence, the deep belief networks is used to model and …explain the large-scale nonlinear trend term of the cyanobacteria bloom spatiotemporal sequence. Then use the time autocorrelation model and the multivariate spatiotemporal autocorrelation model to model and interpret the small-scale residual term; finally, after superimposing the large-scale nonlinear trend term and the small-scale residual term, the adaptive neuro-fuzzy system model is used to predict the chlorophyll a value of the water. Therefore, a fuzzy spatial and temporal sequence prediction method based on fuzzy expert system is proposed. The model verification results show that compared with the existing time series model and single intelligent model, the method can more fully explain the non-stationary and nonlinear dynamic changes of the cyanobacterial bloom spatial-temporal sequence. It provides a new method for accurately predicting cyanobacteria bloom in rivers and lakes. Show more

Keywords: Cyanobacteria bloom prediction, deep belief networks, fuzzy expert system, spatiotemporal sequence

DOI: 10.3233/JIFS-179512

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 1487-1498, 2020