Search scope:
排序: Display mode:
Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
孙曦,吕志民
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9, Pages 1273-1286 doi: 10.1631/FITEE.2200304
Keywords: Point-of-interest recommendation Spatiotemporal effects Long short-term memory (LSTM) Attention mechanism
ECGID: a human identification method based on adaptive particle swarm optimization and the bidirectional LSTM model Research Article
Yefei Zhang, Zhidong Zhao, Yanjun Deng, Xiaohong Zhang, Yu Zhang,zhangyf@hdu.edu.cn,zhaozd@hdu.edu.cn,yanjund@hdu.edu.cn,xhzhang@hdu.edu.cn,zy2009@hdu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 12, Pages 1551-1684 doi: 10.1631/FITEE.2000511
Keywords: 心电图生物特征;个体身份识别;长短期记忆网络;自适应粒子群优化算法
LDformer: a parallel neural network model for long-term power forecasting
田冉,李新梅,马忠彧,刘颜星,王晶霞,王楚
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9, Pages 1287-1301 doi: 10.1631/FITEE.2200540
Keywords: Long-term power forecasting Long short-term memory (LSTM) UniDrop Self-attention mechanism
Enhanced LSTM Model for Daily Runoff Prediction in the Upper Huai River Basin, China Article
Yuanyuan Man, Qinli Yang, Junming Shao, Guoqing Wang, Linlong Bai, Yunhong Xue
Engineering 2023, Volume 24, Issue 5, Pages 230-239 doi: 10.1016/j.eng.2021.12.022
Runoff prediction is of great significance to flood defense. However, due to the complexity and randomness of the runoff process, it is hard to predict daily runoff accurately, especially for peak runoff. To address this issue, this study proposes an enhanced long short-term memory (LSTM) model for runoff prediction, where novel loss functions are introduced and feature extractors are integrated. Two loss functions (peak error tanh (PET), peak error swish (PES)) are designed to strengthen the importance of the peak runoff's prediction while weakening the weight of the normal runoff's prediction. The feature extractor consisting of three LSTM networks is established for each meteorological station, aiming to extract temporal features of the input data at each station. Taking the upper Huai River Basin in China as a case study, daily runoff from 1960–2016 is predicted using the enhanced LSTM model. Results indicate that the enhanced LSTM model performed well, achieving Nash–Sutcliffe efficiency (NSE) coefficient ranging from 0.917–0.924 during the validation period (November 2005–December 2016), outperforming the widely used lumped hydrological models (Australian Water Balance Model (AWBM), Sacramento, SimHyd and Tank Model) and the data-driven models (artificial neural network (ANN), support vector regression (SVR), and gated recurrent units (GRU)). The enhanced LSTM with PES as loss function performed best on extreme runoff prediction with a mean NSE for floods of 0.873. In addition, precipitation at a meteorological station with a higher altitude contributes more runoff prediction than the closest stations. This study provides an effective tool for daily runoff prediction, which will benefit the basin's flood defense and water security management.
Keywords: Runoff prediction Long short-term memory Upper Huai River Basin Extreme runoff Loss function
Dynamic time prediction for electric vehicle charging based on charging pattern recognition Research Article
Chunxi LI, Yingying FU, Xiangke CUI, Quanbo GE
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 2, Pages 299-313 doi: 10.1631/FITEE.2200212
Keywords: Charging mode Charging time Random forest Long short-term memory (LSTM) Simplified particle swarm optimization (SPSO)
High-emitter identification for heavy-duty vehicles by temporal optimization LSTMand an adaptive dynamic threshold Research Article
Zhenyi XU, Renjun WANG, Yang CAO, Yu KANG
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11, Pages 1633-1646 doi: 10.1631/FITEE.2300005
Keywords: High-emitter identification Temporal optimization On-board diagnostic device (OBD) Dynamic threshold
Short-term Load Forecasting Using Neural Network
Luo Mei
Strategic Study of CAE 2007, Volume 9, Issue 5, Pages 77-80
Based on the load data of meritorious power of some area power system, three BP ANN models, namely SDBP, LMBP and BRBP Model, are established to carry out the short-term load forecasting work, and the results are compared. Since the traditional BP algorithm has some unavoidable disadvantages, such as the low training speed and the possibility of being plunged into minimums local minimizing the optimized function, an optimized L-M algorithm, which can accelerate the training of neural network and improve the stability of the convergence, should be applied to forecast to reduce the mean relative error. Bayesian regularization can overcome the over fitting and improve the generalization of ANN.
Keywords: short-term load forecasting(STLF) ANN Levenberg-Marquardt Bayesian regularization optimized algorithms
New results on impulsive type inertial bidirectional associativememory neural networks Research Articles
Chaouki AOUITI, Mahjouba Ben REZEG, Yang CAO
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 2, Pages 324-339 doi: 10.1631/FITEE.1900181
Keywords: Inertial neural networks Anti-periodic solutions Global exponential stability Impulsive effect Time-varying delay Bidirectional associative memory
NIPAD: a non-invasive power-based anomaly detection scheme for programmable logic controllers Article
Yu-jun XIAO, Wen-yuan XU, Zhen-hua JIA, Zhuo-ran MA, Dong-lian QI
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 4, Pages 519-534 doi: 10.1631/FITEE.1601540
Keywords: Industrial control system Programmable logic controller Side-channel Anomaly detection Long short-term memory neural networks
Temporality-enhanced knowledgememory network for factoid question answering Article
Xin-yu DUAN, Si-liang TANG, Sheng-yu ZHANG, Yin ZHANG, Zhou ZHAO, Jian-ru XUE, Yue-ting ZHUANG, Fei WU
Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1, Pages 104-115 doi: 10.1631/FITEE.1700788
Keywords: Question answering Knowledge memory Temporality interaction
Two-Way 4D Printing: A Review on the Reversibility of 3D-Printed Shape Memory Materials
Amelia Yilin Lee, Jia An, Chee Kai Chua
Engineering 2017, Volume 3, Issue 5, Pages 663-674 doi: 10.1016/J.ENG.2017.05.014
The rapid development of additive manufacturing and advances in shape memory materials have fueled the progress of four-dimensional (4D) printing. With the right external stimulus, the need for human interaction, sensors, and batteries will be eliminated, and by using additive manufacturing, more complex devices and parts can be produced. With the current understanding of shape memory mechanisms and with improved design for additive manufacturing, reversibility in 4D printing has recently been proven to be feasible. Conventional one-way 4D printing requires human interaction in the programming (or shape-setting) phase, but reversible 4D printing, or two-way 4D printing, will fully eliminate the need for human interference, as the programming stage is replaced with another stimulus. This allows reversible 4D printed parts to be fully dependent on external stimuli; parts can also be potentially reused after every recovery, or even used in continuous cycles—an aspect that carries industrial appeal. This paper presents a review on the mechanisms of shape memory materials that have led to 4D printing, current findings regarding 4D printing in alloys and polymers, and their respective limitations. The reversibility of shape memory materials and their feasibility to be fabricated using three-dimensional (3D) printing are summarized and critically analyzed. For reversible 4D printing, the methods of 3D printing, mechanisms used for actuation, and strategies to achieve reversibility are also highlighted. Finally, prospective future research directions in reversible 4D printing are suggested.
Keywords: 4D printing Additive manufacturing Shape memory material Smart materials Shape memory alloy Shape memory polymer
Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis Article
Yesheng Xu, Ming Kong, Wenjia Xie, Runping Duan, Zhengqing Fang, Yuxiao Lin, Qiang Zhu, Siliang Tang, Fei Wu, Yu-Feng Yao
Engineering 2021, Volume 7, Issue 7, Pages 1002-1010 doi: 10.1016/j.eng.2020.04.012
Infectious keratitis is the most common condition of corneal diseases in which a pathogen grows in the cornea leading to inflammation and destruction of the corneal tissues. Infectious keratitis is a medical emergency for which a rapid and accurate diagnosis is needed to ensure prompt and precise treatment to halt the disease progression and to limit the extent of corneal damage; otherwise, it may develop a sight threatening and even eye-globe-threatening condition. In this paper, we propose a sequentiallevel deep model to effectively discriminate infectious corneal disease via the classification of clinical images. In this approach, we devise an appropriate mechanism to preserve the spatial structures of clinical images and disentangle the informative features for clinical image classification of infectious keratitis. In a comparison, the performance of the proposed sequential-level deep model achieved 80% diagnostic accuracy, far better than the 49.27% ± 11.5% diagnostic accuracy achieved by 421 ophthalmologists over 120 test images.
Keywords: Deep learning Corneal disease Sequential features Machine learning Long short-term memory
Short-Range Current Velocity Records to Apply in the Reference Period for Sutong Bridge
Su Hui,Gong Weiming,Liang Shuting
Strategic Study of CAE 2006, Volume 8, Issue 7, Pages 42-46
The current velocity of reference period is determined by the local primitive data. A method is introduced to determine the current velocity of reference period through short-range current velocity records for the area that lacks of long-range current velocity records. According to short-range current velocity records of Sutong Bridge the probability distribute mode of the current velocity is established. Presuming the extreme value by way of minority sample,the current velocity of reference period is calculated.Correlation analysis is carried out, the rationality of the calculation is validated and the regression equation is established. The calculated results provide credible technical guide to devise and construct Sutong Bridge and ensure current and wave resistance safety.
Keywords: short-range records the current velocity of reference period correlation analysis regression equation
Fractional-order memristive neural synaptic weighting achieved by pulse-based fracmemristor bridge circuit Research Articles
Yifei Pu, Bo Yu, Qiuyan He, Xiao Yuan,heqiuyan789@163.com,yuanxiao@scu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 6, Pages 862-876 doi: 10.1631/FITEE.2000085
Keywords: 分数阶微积分;分忆抗;分忆抗值;分数阶忆阻;分数阶记忆性突触
Zheng Jinlong,Shu Siyun,Liu Songhao,Guo Zhouyi,Wu Yongming,Bao Xinmin,Zhang Zengqiang,Jin Mei,Ma Hanzhang
Strategic Study of CAE 2008, Volume 10, Issue 5, Pages 38-45
This paper is to investigate the activated brain areas and the neuronal mechanism of Chinese paired-word associated learning and memory in healthy volunteers by functional magnetic resonance imaging (fMRI) technique. 16 right-handed normal volunteers participated in a test of paired-word associated learning and memory, while the fMRI data were recorded. Control tasks were performed for the block-design. SPM 99 was used to analyze the data and to get the activated brain regions. 14 volunteers passed the paired-word associated learning and memory task. Both cortex and subcortical structures were activated. The brain cortex areas include the bilateral frontal lobes, the bilateral parietal lobes, the bilateral occipital lobes, the bilateral cingulate gyrus and the bilateral parahippocampal gyrus with extremely left hemisphere predominance and the left temporal lobe were activated by both coding and retrieval stages of the paired-word associated learning and memory task. The subcortical structures including the striatum and its marginal division (MrD) were activated with left predominance, the caudate and the thalamus were also activated during the tasks. However, the left occipital lobe and the middle and inferior frontal gyrus of the left frontal lobe were more activative than others in scope and brightness during the coding stage of the paired-word associated learning and memory task, while the left parietal lobe and dorsolateral part of the middle frontal gyrus were more activative than others in scope and brightness during the retrieval stage of the paired-word associated learning and memory task. The left middle and inferior frontal gyrus of the frontal lobe, the left lateral parts of the occipital lobe, the left superior lobule and supramarginal gyrus and the angular gyrus of the parietal lobe might play more important roles in the paired-word associated learning and memory task than the rest of the cortex. The MrD of the striatum was mainly involved in coding stages of the paired-word associated learning and memory task. The results of this study revealed that the subcortical structures mainly the striatum as well as the cortex were involved in the associated learning and memory of language in human brain. The transform of activated brain areas from the coding stage to the retrieval stage of the Chinese paired-word learning and memory was described and its neural mechanism was discussed.
Keywords: functional magnetic resonance imaging (fMRI) of human brain paired-word language associated learning and memory cortex and subcortical structures
Title Author Date Type Operation
Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
孙曦,吕志民
Journal Article
ECGID: a human identification method based on adaptive particle swarm optimization and the bidirectional LSTM model
Yefei Zhang, Zhidong Zhao, Yanjun Deng, Xiaohong Zhang, Yu Zhang,zhangyf@hdu.edu.cn,zhaozd@hdu.edu.cn,yanjund@hdu.edu.cn,xhzhang@hdu.edu.cn,zy2009@hdu.edu.cn
Journal Article
LDformer: a parallel neural network model for long-term power forecasting
田冉,李新梅,马忠彧,刘颜星,王晶霞,王楚
Journal Article
Enhanced LSTM Model for Daily Runoff Prediction in the Upper Huai River Basin, China
Yuanyuan Man, Qinli Yang, Junming Shao, Guoqing Wang, Linlong Bai, Yunhong Xue
Journal Article
Dynamic time prediction for electric vehicle charging based on charging pattern recognition
Chunxi LI, Yingying FU, Xiangke CUI, Quanbo GE
Journal Article
High-emitter identification for heavy-duty vehicles by temporal optimization LSTMand an adaptive dynamic threshold
Zhenyi XU, Renjun WANG, Yang CAO, Yu KANG
Journal Article
New results on impulsive type inertial bidirectional associativememory neural networks
Chaouki AOUITI, Mahjouba Ben REZEG, Yang CAO
Journal Article
NIPAD: a non-invasive power-based anomaly detection scheme for programmable logic controllers
Yu-jun XIAO, Wen-yuan XU, Zhen-hua JIA, Zhuo-ran MA, Dong-lian QI
Journal Article
Temporality-enhanced knowledgememory network for factoid question answering
Xin-yu DUAN, Si-liang TANG, Sheng-yu ZHANG, Yin ZHANG, Zhou ZHAO, Jian-ru XUE, Yue-ting ZHUANG, Fei WU
Journal Article
Two-Way 4D Printing: A Review on the Reversibility of 3D-Printed Shape Memory Materials
Amelia Yilin Lee, Jia An, Chee Kai Chua
Journal Article
Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis
Yesheng Xu, Ming Kong, Wenjia Xie, Runping Duan, Zhengqing Fang, Yuxiao Lin, Qiang Zhu, Siliang Tang, Fei Wu, Yu-Feng Yao
Journal Article
Short-Range Current Velocity Records to Apply in the Reference Period for Sutong Bridge
Su Hui,Gong Weiming,Liang Shuting
Journal Article
Fractional-order memristive neural synaptic weighting achieved by pulse-based fracmemristor bridge circuit
Yifei Pu, Bo Yu, Qiuyan He, Xiao Yuan,heqiuyan789@163.com,yuanxiao@scu.edu.cn
Journal Article
The brain areas and the neural mechanism involved in the Chinese paired-word associated learning and memory in healthy volunteers——a brain functional magnetic resonance imaging study
Zheng Jinlong,Shu Siyun,Liu Songhao,Guo Zhouyi,Wu Yongming,Bao Xinmin,Zhang Zengqiang,Jin Mei,Ma Hanzhang
Journal Article