Yantao Li
Southwest University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Yantao Li.
Neural Computing and Applications | 2011
Yantao Li; Shaojiang Deng; Di Xiao
An algorithm for constructing a one-way novel Hash function based on two-layer chaotic neural network structure is proposed. The piecewise linear chaotic map (PWLCM) is utilized as transfer function, and the 4-dimensional and one-way coupled map lattices (4D OWCML) is employed as key generator of the chaotic neural network. Theoretical analysis and computer simulation indicate that the proposed algorithm presents several interesting features, such as high message and key sensitivity, good statistical properties, collision resistance and secure against meet-in-the-middle attacks, which can satisfy the performance requirements of Hash function.
real time technology and applications symposium | 2013
Xin Qi; Matthew Keally; Gang Zhou; Yantao Li; Zhen Ren
In a Body Sensor Network (BSN) activity recognition system, sensor sampling and communication quickly deplete battery reserves. While reducing sampling and communication saves energy, this energy savings usually comes at the cost of reduced recognition accuracy. To address this challenge, we propose AdaSense, a framework that reduces the BSN sensors sampling rate while meeting a user-specified accuracy requirement. AdaSense utilizes a classifier set to do either multi-activity classification that requires a high sampling rate or single activity event detection that demands a very low sampling rate. AdaSense aims to utilize lower power single activity event detection most of the time. It only resorts to higher power multi-activity classification to find out the new activity when it is confident that the activity changes. Furthermore, AdaSense is able to determine the optimal sampling rates using a novel Genetic Programming algorithm. Through this Genetic Programming approach, AdaSense reduces sampling rates for both lower power single activity event detection and higher power multi-activity classification. With an existing BSN dataset and a smartphone dataset we collect from eight subjects, we demonstrate that AdaSense effectively reduces BSN sensors sampling rate and outperforms a state-of-the-art solution in terms of energy savings.
Neural Computing and Applications | 2011
Yantao Li; Di Xiao; Shaojiang Deng; Qi Han; Gang Zhou
A parallel Hash algorithm construction based on chaotic maps with changeable parameters is proposed and analyzed in this paper. The two main characteristics of the proposed algorithm are parallel processing mode and message expansion. The algorithm translates the expanded message blocks into the corresponding ASCII code values as the iteration times, iterates the chaotic asymmetric tent map and then the chaotic piecewise linear map, continuously, with changeable parameters dynamically obtained from the position index of the corresponding message blocks, to generate decimal fractions, then rounds the decimal fractions to integers, and finally cascades these integers to construct intermediate Hash value. Final Hash value with the length of 128-bit is generated by logical XOR operation of intermediate Hash values. Theoretical analysis and computer simulation indicate that the proposed algorithm satisfies the performance requirements of a secure Hash function.
Information Sciences | 2012
Yantao Li; Di Xiao; Shaojiang Deng
In this paper, we present a novel keyed hash function based on a dynamic lookup table of functions. More specifically, we first exploit the piecewise linear chaotic map (PWLCM) with secret keys used for producing four 32-bit initial buffers and then elaborate the lookup table of functions used for selecting composite functions associated with messages. Next, we convert the divided message blocks into ASCII code values, check the equivalent indices and then find the associated composite functions in the lookup table of functions. For each message block, the four buffers are reassigned by the corresponding composite function and then the lookup table of functions is dynamically updated. After all the message blocks are processed, the final 128-bit hash value is obtained by cascading the last reassigned four buffers. Finally, we evaluate our hash function and the results demonstrate that the proposed hash algorithm has good statistical properties, strong collision resistance, high efficiency, and better statistical performance compared with existing chaotic hash functions.
IEEE Access | 2016
Dawen Xia; Huaqing Li; Binfeng Wang; Yantao Li; Zili Zhang
In big-data-driven traffic flow prediction systems, the robustness of prediction performance depends on accuracy and timeliness. This paper presents a new MapReduce-based nearest neighbor (NN) approach for traffic flow prediction using correlation analysis (TFPC) on a Hadoop platform. In particular, we develop a real-time prediction system including two key modules, i.e., offline distributed training (ODT) and online parallel prediction (OPP). Moreover, we build a parallel
Neural Computing and Applications | 2013
Yantao Li; Di Xiao; Shaojiang Deng; Gang Zhou
k
Neural Computing and Applications | 2017
Yantao Li; Xiang Li; Xiangwei Liu
-nearest neighbor optimization classifier, which incorporates correlation information among traffic flows into the classification process. Finally, we propose a novel prediction calculation method, combining the current data observed in OPP and the classification results obtained from large-scale historical data in ODT, to generate traffic flow prediction in real time. The empirical study on real-world traffic flow big data using the leave-one-out cross validation method shows that TFPC significantly outperforms four state-of-the-art prediction approaches, i.e., autoregressive integrated moving average, Naïve Bayes, multilayer perceptron neural networks, and NN regression, in terms of accuracy, which can be improved 90.07% in the best case, with an average mean absolute percent error of 5.53%. In addition, it displays excellent speedup, scaleup, and sizeup.
Multimedia Tools and Applications | 2016
Yantao Li; Gang Zhou; Daniel Graham; Andrew Holtzhauer
In this paper, we reconsider and analyze our previous paper a novel hash algorithm construction based on chaotic neural network, then present equal-length and unequal-length forgery attacks against its security in detail, and then propose a significantly improved approach by utilizing a method of complicated nonlinear computation to enhance the security of the original hash algorithm. Theoretical analysis and computer simulation indicate that the improved algorithm can completely resist the two kinds of forgery attacks and also shows other better performance than the original one, such as better message and key sensitivity, statistical properties, which can satisfy the performance requirements of a more secure hash function.
IEEE Transactions on Multimedia | 2016
Xin Qi; Qing Yang; David T. Nguyen; Ge Peng; Gang Zhou; Bo Dai; Daqing Zhang; Yantao Li
We present a fast and efficient hash algorithm based on a generalized chaotic mapping with variable parameters in this paper. We first define a generalized chaotic mapping by utilizing piecewise linear chaotic map and trigonometric functions. Then, we convert the arbitrary length of message into the corresponding ASCII values and perform 6-unit iterations with variable parameters and message values based on the generalized chaotic mapping. The final hash value is obtained by cascading extracted bits from iteration state values. We excessively evaluate the proposed algorithm in terms of distribution of hash value, sensitivity of hash value to the message and secret keys, statistical analysis of diffusion and confusion, analysis of birthday attacks and collision resistance, analysis of secret keys, analysis of speed, and comparison with other algorithms, and the results illustrate that the suggested algorithm is fast, efficient, and enough simple and has good confusion and diffusion capabilities, strong collision resistance, and a high level of security.
Multimedia Tools and Applications | 2016
Yantao Li; Gang Zhou; Yue Li; Du Shen
According to New York Times, 5.6 million people in the United States are paralyzed to some degree. Motivated by requirements of these paralyzed patients in controlling assisted-devices that support their mobility, we present a novel EEG-based BCI system, which is composed of an Emotive EPOC neuroheadset, a laptop and a Lego Mindstorms NXT robot in this paper. We provide online learning algorithms that consist of k-means clustering and principal component analysis to classify the signals from the headset into corresponding action commands. Moreover, we also discuss how to integrate the Emotiv EPOC headset into the system, and how to integrate the LEGO robot. Finally, we evaluate the proposed online learning algorithms of our BCI system in terms of precision, recall, and the F-measure, and our results show that the algorithms can accurately classify the subjects’ thoughts into corresponding action commands.