Journal of Intelligent & Fuzzy Systems - Volume 37, issue 4

Authors: Zhao, Zhongtang | Zhao, Xuezhuan | Li, Lingling

Article Type: Research Article

Abstract: In the field of big data machine learning, the data volume is large, but the labeled data is few. Due to this, it may lead to that the distribution of labeled data (source domain) is not similar to that of unlabeled data (target domain). In traditional machine learning field, this problem is a kind of transfer learning problems. To address this problem, a self labeling online sequential extreme learning machine is presented, which is called SLOSELM. Firstly, an ELM classifier is trained on the labeled training dataset of the source domain. Secondly, the unlabelled dataset of the target domain is …classified by the ELM classifier. In the third step, the high confident samples are selected and the OSELM is employed to update the original ELM classifier. Tested on the real-world image dataset and the daily activity dataset, the results show that our algorithm performs well. Show more

Keywords: Extreme learning machine, activity recognition, transfer learning, big data, pervasive computing

DOI: 10.3233/JIFS-179281

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4485-4491, 2019

Authors: Zhao, Hongwei | Liu, Yuqi | Huang, Yongping | Lu, Xuwang | Tu, Xiaohang

Article Type: Research Article

Abstract: Aiming at the problem of low prediction accuracy and slow training time for Neural network with single hidden layer forecast, this paper proposes a combination of Multitask and DBN Neural network used to predict the short-term free parking berths. Firstly, the DBN Neural Network is used to carry out auto correlation analysis of the original data, and the characteristics of the data inclusion are obtained. Combined with Multitask Learning, the paper studies several related tasks simultaneously, the Neural Network can have the knowledge to new things for forecasting, and compared with the existing Neural network with single hidden layer, the …data preprocessing process is reduced and better prediction results are obtained. The results show that this method shortens the training time and improves the prediction results. Show more

Keywords: Free parking berths, multitask learning, DBN neural network

DOI: 10.3233/JIFS-179282

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4493-4498, 2019

Authors: Zhang, Yongli | Han, Tailin | Lang, Baihe | Li, Yang | Lai, Fuwen

Article Type: Research Article

Abstract: The shockwave signal is affected by the weapon launch and the external environment, and it is often mixed with many kinds of noise, some even submerged. To detect and extract the shockwave signal under low signal-to-noise ratio, the transient signal SNR, the power-law detector of the higher-order cumulant spectrum (HOCS) and the Dual-tree complex wavelet transform (DTCWT) extraction model are proposed in the study. The average power of noise under different SNR was calculated by comparing the average power of the background noise with the instantaneous power of the shockwave. Based on the power-law detection of HOCS, the power-law of …the two spectra was analyzed. After the DTCWT, the optimal threshold of the maximum posterior estimation was denoted by layer by layer, then the shockwave signal was extracted by the inverse transform, and the validity of the model was verified by the measured data. Results demonstrate that the signal to noise ratio of the transient signal can reflect the true magnitude of the average power of the noise, and the conventional SNR reduces the average power of the noise, and the error ratio is up to 70%. The power-law detector of bispectrum diagonals has the good effect on Gaussian white noise suppression, and can detect the signal to noise ratio of -15dB. The DTCWT can realize multiple peak shockwave extraction with the smaller amplitude, and the mean square error (MSE) of measured signal extraction can reach 0.0189. The proposed method provides a good reference for the detection of shockwave signal and the extraction of the multi-peak waveform in low signal-to-noise ratio. Show more

Keywords: Shockwave, power-law detector, high order spectral transform, dual-tree complex wavelet transform

DOI: 10.3233/JIFS-179283

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4499-4510, 2019

Authors: Ding, Xiaobing | Liu, Zhigang | Hu, Hua | Huang, Yuanchun | Yu, Jie

Article Type: Research Article

Abstract: In this work, we proposed a new systematic metro operation risk identification method (MORIM) and risk grade classification method (RGLM) based on the daily dispatching fault log. We collected and analysed the operation risks during Metro operation, and the database SQL was designed for calculating the probability of risks. Then, we converted the equipment malfunction, train delay, large passenger flow etc. to time delay, so as to realize the quantitative calculation of the risks. We clustered risk sources by data mining, from which, we can get the risk cluster centre, and the emergency response scheme can be accurately made to …match the clustered risks. Finally, the systematic method was validated by a case study. It was found that the method was accurate and the conclusion was reliable. This paper can provide theory and decision support for Metro operation safety management and it has good practical significance for larger cities to dispose the conditions of large passenger flow. Show more

Keywords: Intelligent identification algorithm, fault log, data mining, operation risks, urban rail transportation

DOI: 10.3233/JIFS-179284

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4511-4522, 2019

Authors: Zhou, Weifeng | Hou, Juan | Fan, Wei | Dai, Yang

Article Type: Research Article

Abstract: In this study, we develop a kind of location-based marine fishery information service method. The method is to use position and communication function of BeiDou navigation satellite system and shipborne marine environment monitoring sensors to obtain the location information, production data and marine environment data measured in situ, and then to extract the grid data around the target fishing vessel and transform these data into environment data in the form of vector. Then information service center takes the production data and environment data measured in situ as training sample to optimize the set fishing ground forecast model in accuracy and …generalization. The model is used to calculate the fishing ground probability around the target fishing vessel. Finally, the information service center encodes the result of the forecast and related environment information together and send them to the target vessel. The method providing a location-based, vessel-oriented, customized and high-precision service, data generated from which is far less than those from some traditional methods, is cost-effective and easy to be popularized and applied by fishery operation departments. Show more

Keywords: Marine fishery, information service, satellite navigation communication system, fishing ground forecasting

DOI: 10.3233/JIFS-179285

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4523-4530, 2019

Authors: Ji, Wenjiang | Zhu, Lei | Wang, Yichuan | Liu, Zheng | Hei, Xinhong

Article Type: Research Article

Abstract: Vehicular ad hoc networks (VANET) is seen as an effective solution to ensure the driving safety and efficiency. As a key foundation, the road side unit (RSU) connect with each other to form a backbone network in VANET. The authentication of RSUs is the main tasks to prevent the secure communication in VANET suffering from various attacks caused by cunning adversaries. In this paper, we propose a new type of verifiable secret sharing (VSS) scheme based on bivariate polynomial to achieving the RSU authentication in a secret sharing way. Our proposed VSS based authentication includes two phases. In phase 1, …the t RSUs that participate in secret reconstruction collaborate to detect whether there exist illegitimate ones; in phase 2, the t legitimate RSUs reveal their shares for secret reconstruction, and the fake shares can be identified. Our VSS facilitates the RSU authentication since (1) any RSUs participate in secret reconstruction can be confirmed legitimate, (2) any fake shares revealed in secret reconstruction can be identified, (3) a globalized group temporary session key will be established after the VSS process. In addition, our VSS scheme is unconditional secure since the security of our VSS is not based on any computational assumption. Show more

Keywords: Vehicular ad hoc networks, security, RSU authentication, verifiable secret sharing

DOI: 10.3233/JIFS-179286

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4531-4536, 2019

Authors: Cao, Yan | Wei, Wanyu | Huang, Liang | Qiao, Hu | Du, Jiang

Article Type: Research Article

Abstract: Uncertain sporadic risks have prominent features such as small probability, difficult to predict, fast diffusion, and complex types, which greatly increase the difficulty of control. Severe incidental risk events often affect the normal operation of the supply chain system, so it is particularly important to respond to risks in a timely and effective manner. Based on fuzzy logic, this paper studies the coping strategies of three-level supply chain systems composed of manufacturers, distribution centers and retailers under uncertain risks. Firstly, fuzzy logic is used to highly quantify fuzzy variables to calculate specific changes caused by the uncertain risks to members …in supply chain, and effectively predict overall changes of the supply chain system; Secondly, the member information is updated in the post-change supply chain system. On this basis, the member maximum loss model is established, the maximum loss amount and the amount of each strategy loss are calculated, and a risk response strategy plan is formulated. Finally, a coping strategy is stored for a quick call when similar risks occur again. The feasibility and effectiveness of the model and method are verified by specific examples and variable sensitivity analysis. Show more

Keywords: Manufacturing supply chain, risk response, maximum loss, decision analysis, fuzzy logic

DOI: 10.3233/JIFS-179287

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4537-4546, 2019

Authors: Wei, Xinyuan | Zang, Hongyan

Article Type: Research Article

Abstract: This paper proposes two kind of new cubic chaotic maps based on Li-Yorke’s chaos criterion theorem, and gives the corresponding chaos discriminant conditions. The dynamical behaviors of systems are numerically simulated by nonlinear techniques including bifurcation diagrams and Laypunov exponents, and the simulation results show the cubic chaotic maps display chaotic characteristics as the provided theorems expect. Using spectral entropy algorithm, this paper analyses the complexity of chaotic sequences generated by cubic chaotic maps after quantitative process, and further compares the complexity of the chaotic pseudorandom sequences based on different quantitative methods. The results show different quantitative methods has a …significant effect on the complexity of chaotic sequences; the pseudorandom sequences generated by the systems and quantitative method provided in this paper turns to have a better complexity. The above conclusions provide a theoretical basis for generating pseudorandom sequences with better quality. Show more

Keywords: Cubic chaotic maps, lyapunov exponent, spectral entropy, complexity

DOI: 10.3233/JIFS-179288

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4547-4555, 2019

Authors: Yi, Haibo

Article Type: Research Article

Abstract: Over the past few years, there has been a sustaining interest in research of secure communication architectures and protocols based on asymmetric cryptographic techniques. However, it is showed that quantum computers can break most asymmetric cryptographic techniques and they will be insecure. In this paper, we focus on accelerating quantum-safe cryptography for communication systems by improving inversions in finite fields. Cellular Automaton (CA) is a discrete model in mathematics, physics, computer science and neural computing. It is a grid of cells with a finite number of states and it has been adopted and applied to many research and engineering fields, …e.g., cryptography and neural computing. In addition, cellular automata can simulate many real-world systems, such as biological system, Vehicular Communication (VC) systems and neural networks. We propose a variant of Fermat’s theorem inversion based on cellular automaton. We implement inversions in finite fields on Application Specific Integrated Circuit (ASIC) and accelerate some quantum-safe signature schemes, which shows that they are efficient for constructing quantum-safe communications. Show more

Keywords: Cellular automaton (CA), inversions, neural network

DOI: 10.3233/JIFS-179289

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4557-4562, 2019

Authors: Wang, Shu | Yu, Qiang | Zhao, Xuan | Zhang, Shuo | Ye, Yiming

Article Type: Research Article

Abstract: Vehicle sideslip angle is the key parameter to evaluate the handling stability of the vehicle, and it is also one of the control targets of the vehicle stability, so the accurate estimation of the vehicle sideslip angle directly affects the safety of the vehicle. In order to improve the influence of particles degeneracy on the estimation of vehicle sideslip angle, and ensure the nonnegative qualitative of the covariance matrix and iterative stability of the unscented Kalman filter algorithm, in this paper, a vehicle sideslip angle estimation method based on singular value decomposition Unscented Kalman particle filtering algorithm (SVD-UPF) is proposed …by using two-degrees-of-freedom nonlinear vehicle dynamics model, and the singular value decomposition Unscented Kalman filter algorithm is used to optimize the density distribution function. Using the hardware-in-the-loop simulation platform of distributed drive electric vehicle (HEV), the method of estimating the vehicle sideslip angle based on the unscented Kalman filter(UKF) and the SVD-UPF algorithm is compared and verified under the working condition of emergency double lane change, steering angle increase gradually, steering wheel angle stepping. The results show that the SVD-UPF estimator improves the accuracy of the unscented Kalman filter estimator and the effectiveness of the algorithm is verified. Show more

Keywords: Sideslip angle estimation, singular value decomposition, unscented kalman particle filter algorithm, accuracy

DOI: 10.3233/JIFS-179290

Citation: Journal of Intelligent & Fuzzy Systems, vol. 37, no. 4, pp. 4563-4573, 2019