Relationship between physical activity and specific working memory indicators of depressive symptoms in university students

BACKGROUND The detection rate of depression among university students has been increasing in recent years,becoming one of the main psychological diseases that endangers their physical and mental health.According to statistics,self-harm and suicide,for which there is no effective intervention,are the second leading causes of death.AIM To explore the relationship between different elements and levels of physical activity and college students’depression-symptom-specific working memory indicators.METHODS Of 143 college students were analyzed using the Beck Depression Self-Rating Scale,the Physical Activity Rating Scale,and the Working Memory Task.RESULTS There was a significant difference between college students with depressive symptoms and healthy college students in completing verbal and spatial working memory(SWM)tasks correctly(all P<0.01).Physical Activity Scale-3 scores were significantly and positively correlated with the correct rate of the verbal working memory task(r=0.166)and the correct rate of the SWM task(r=0.210)(all P<0.05).There were significant differences in the correct rates of verbal and SWM tasks according to different exercise intensities(all P<0.05)and different exercise durations(all P<0.05),and no significant differences in the correct rates of verbal and SWM tasks by exercise frequency(all P>0.05).CONCLUSION An increase in physical exercise among college students,particularly medium-and high-intensity exercise and exercise of 30 min or more,can improve the correct rate of completing working memory tasks.

Text Difficulty,Working Memory Capacity and Mind Wandering During Chinese EFL Learners’Reading

This experimental study investigated how text difficulty and different working memory capacity(WMC)affected Chinese EFL learners’reading comprehension and their tendency to engage in task-unrelated thoughts,that is,mind wandering(MW),in the course of reading.Sixty first-year university non-English majors participated in the study.A two-factor mixed experimental design of 2(text difficulty:difficult and simple)×2(WMC:high/large and low/small)was employed.Results revealed that 1)the main and interaction effects of WMC and text difficulty on voluntary MW were significant,whereas those on involuntary MW were not;2)while reading the easy texts,the involuntary MW of high-WMC individuals was less frequent than that of low-WMC ones,whereas while reading the difficult ones,the direct relationship between WMC and involuntary MW was not found;and that 3)high-WMC individuals had a lower overall rate of MW and better reading performance than low-WMC individuals did,but with increasing text difficulty,their rates of overall MW and voluntary MW were getting higher and higher,and the reading performance was getting lower and lower.These results lend support to WM theory and have pedagogical implications for the instruction of L2 reading.

Positive Effect of Transcranial Direct Current Stimulation on Visual Verbal Working Memory in Patients with Attention-Deficit/Hyperactivity Disorder

Background: Working memory is an executive function that plays an important role in many aspects of daily life, and its impairment in patients with attention-deficit/hyperactivity disorder (ADHD) affects quality of life. The dorsolateral prefrontal cortex (DLPFC) has been a good target site for transcranial direct current stimulation (tDCS) due to its intense involvement in working memory. In our 2018 study, tDCS improved visual-verbal working memory in healthy subjects. Objective: This study examines the effects of tDCS on ADHD patients, particularly on verbal working memory. Methods: We conducted an experiment involving verbal working memory of two modalities, visual and auditory, and a sustained attention task that could affect working memory in 9 ADHD patients. Active or sham tDCS was applied to the left DLPFC in a single-blind crossover design. Results: tDCS significantly improved the accuracy of visual-verbal working memory. In contrast, tDCS did not affect auditory-verbal working memory and sustained attention. Conclusion: tDCS to the left DLPFC improved visual-verbal working memory in ADHD patients, with important implications for potential ADHD treatments.

Slope stability prediction based on a long short-term memory neural network:comparisons with convolutional neural networks,support vector machines and random forest models

The numerical simulation and slope stability prediction are the focus of slope disaster research.Recently,machine learning models are commonly used in the slope stability prediction.However,these machine learning models have some problems,such as poor nonlinear performance,local optimum and incomplete factors feature extraction.These issues can affect the accuracy of slope stability prediction.Therefore,a deep learning algorithm called Long short-term memory(LSTM)has been innovatively proposed to predict slope stability.Taking the Ganzhou City in China as the study area,the landslide inventory and their characteristics of geotechnical parameters,slope height and slope angle are analyzed.Based on these characteristics,typical soil slopes are constructed using the Geo-Studio software.Five control factors affecting slope stability,including slope height,slope angle,internal friction angle,cohesion and volumetric weight,are selected to form different slope and construct model input variables.Then,the limit equilibrium method is used to calculate the stability coefficients of these typical soil slopes under different control factors.Each slope stability coefficient and its corresponding control factors is a slope sample.As a result,a total of 2160 training samples and 450 testing samples are constructed.These sample sets are imported into LSTM for modelling and compared with the support vector machine(SVM),random forest(RF)and convo-lutional neural network(CNN).The results show that the LSTM overcomes the problem that the commonly used machine learning models have difficulty extracting global features.Furthermore,LSTM has a better prediction performance for slope stability compared to SVM,RF and CNN models.

Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis

A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.

An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning and operating traffic structures.This study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning process.The fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal relationships.Firstly,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition model.The second aspect involves predicting traffic volume using the long short-term memory algorithm.Next,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent optimization.Finally,the fusion of the obtained results leads to a final traffic volume prediction.The experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and R-squared.The achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the competing.These findings highlight the accuracy of traffic pattern prediction.Consequently,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.

Integrating Transformer and Bidirectional Long Short-Term Memory for Intelligent Breast Cancer Detection from Histopathology Biopsy Images

Breast cancer is a significant threat to the global population,affecting not only women but also a threat to the entire population.With recent advancements in digital pathology,Eosin and hematoxylin images provide enhanced clarity in examiningmicroscopic features of breast tissues based on their staining properties.Early cancer detection facilitates the quickening of the therapeutic process,thereby increasing survival rates.The analysis made by medical professionals,especially pathologists,is time-consuming and challenging,and there arises a need for automated breast cancer detection systems.The upcoming artificial intelligence platforms,especially deep learning models,play an important role in image diagnosis and prediction.Initially,the histopathology biopsy images are taken from standard data sources.Further,the gathered images are given as input to the Multi-Scale Dilated Vision Transformer,where the essential features are acquired.Subsequently,the features are subjected to the Bidirectional Long Short-Term Memory(Bi-LSTM)for classifying the breast cancer disorder.The efficacy of the model is evaluated using divergent metrics.When compared with other methods,the proposed work reveals that it offers impressive results for detection.

Landslide displacement prediction based on optimized empirical mode decomposition and deep bidirectional long short-term memory network

There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement and time series of a landslide.The second one is the dynamic evolution of a landslide,which could not be feasibly simulated simply by traditional prediction models.In this paper,a dynamic model of displacement prediction is introduced for composite landslides based on a combination of empirical mode decomposition with soft screening stop criteria(SSSC-EMD)and deep bidirectional long short-term memory(DBi-LSTM)neural network.In the proposed model,the time series analysis and SSSC-EMD are used to decompose the observed accumulated displacements of a slope into three components,viz.trend displacement,periodic displacement,and random displacement.Then,by analyzing the evolution pattern of a landslide and its key factors triggering landslides,appropriate influencing factors are selected for each displacement component,and DBi-LSTM neural network to carry out multi-datadriven dynamic prediction for each displacement component.An accumulated displacement prediction has been obtained by a summation of each component.For accuracy verification and engineering practicability of the model,field observations from two known landslides in China,the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation.The case study verified that the model proposed in this paper can better characterize the"stepwise"deformation characteristics of a slope.As compared with long short-term memory(LSTM)neural network,support vector machine(SVM),and autoregressive integrated moving average(ARIMA)model,DBi-LSTM neural network has higher accuracy in predicting the periodic displacement of slope deformation,with the mean absolute percentage error reduced by 3.063%,14.913%,and 13.960%respectively,and the root mean square error reduced by 1.951 mm,8.954 mm and 7.790 mm respectively.Conclusively,this model not only has high prediction accuracy but also is more stable,which can provide new insight for practical landslide prevention and control engineering.

Device Anomaly Detection Algorithm Based on Enhanced Long Short-Term Memory Network

The problems in equipment fault detection include data dimension explosion,computational complexity,low detection accuracy,etc.To solve these problems,a device anomaly detection algorithm based on enhanced long short-term memory(LSTM)is proposed.The algorithm first reduces the dimensionality of the device sensor data by principal component analysis(PCA),extracts the strongly correlated variable data among the multidimensional sensor data with the lowest possible information loss,and then uses the enhanced stacked LSTM to predict the extracted temporal data,thus improving the accuracy of anomaly detection.To improve the efficiency of the anomaly detection,a genetic algorithm(GA)is used to adjust the magnitude of the enhancements made by the LSTM model.The validation of the actual data from the pumps shows that the algorithm has significantly improved the recall rate and the detection speed of device anomaly detection,with the recall rate of 97.07%,which indicates that the algorithm is effective and efficient for device anomaly detection in the actual production environment.

THE RELATION BETWEEN EVOLUTION OF SPATIAL WORKING MEMORY FUNCTION AND OF MORPHOLOGY OF THE DORSOLATERAL PREFRONTAL CORTEX AMONG THE RHESUS MONKEY, SLOW LORIS AND TREE SHREW

The relation between evolution of spatial working memory function and of morphology of the dorsolateral prefrontal cortex among the rhesus monkey (Macaca mulatta), the slow loris (Nycticebus coucang) and the tree shrew (Tupaia belangen chinensis) were reported in present paper. The results read as follows: In the DR performance with training, the rhesus monkeys and slow lorises could reach a criterion of 90% correct response at 1.1 ± 3.2 seconds, and 3.8±0.4 seconds delay interval, respectively, by 1000 training trails. The tree shrews failed to reach the criterion of 90% correct response even at 0 seconds delay interval by 1000 training trails. If a delay interval was tested in one session (30 trails) only, doing the DR performamce without training, the rhesus monkeys reached a correct of 80% or higher in each session at 0, 1, 2, 3, 4, and 5 seconds delay, respectively. The percent correct in each session of the slow lorises showed no differences from the rhesus monkeys at 0, 1, 2, 3, and 4 seconds delay. However, when the delay interval was increased to 5 seconds, the percent correct of the DR performance declined to 70% or lower in the slow lorises. In the tree shrews the percent correct in each session reached to 70% or lower at 0, 1, 2, 3, 4, and 5 seconds delay interval, respectively. The morphological studies revealed that the size of the prefrontal cortex increased, and the structure got complex in the course of the evolution in primates. It is suggested that the relation of evolution between the spatial working memory function and anatomy in the prefrontal cortex might be significant among the three species, both the development of morphology and that of the spatial working memory function in the dorsolateral prefrontal cortex are later than other regions of cerebral cortex in phylogenetic evolution course.

Short-Term Wind Power Prediction Based on ICEEMDAN-SE-LSTM Neural Network Model with Classifying Seasonal

Wind power prediction is very important for the economic dispatching of power systems containing wind power.In this work,a novel short-term wind power prediction method based on improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)and(long short-term memory)LSTM neural network is proposed and studied.First,the original data is prepossessed including removing outliers and filling in the gaps.Then,the random forest algorithm is used to sort the importance of each meteorological factor and determine the input climate characteristics of the forecast model.In addition,this study conducts seasonal classification of the annual data where ICEEMDAN is adopted to divide the original wind power sequence into numerous modal components according to different seasons.On this basis,sample entropy is used to calculate the complexity of each component and reconstruct them into trend components,oscillation components,and random components.Then,these three components are input into the LSTM neural network,respectively.Combined with the predicted values of the three components,the overall power prediction results are obtained.The simulation shows that ICEEMDAN-SE-LSTM achieves higher prediction accuracy ranging from 1.57%to 9.46%than other traditional models,which indicates the reliability and effectiveness of the proposed method for power prediction.

Working Memory in Language Use

This paper investigates the working memory in two aspects of language use, vocabulary acquisition and language comprehension. It is involved both in language acquisition and second language learning.

Working-memory training improves developmental dyslexia in Chinese children

Although plasticity in the neural system underlies working memory, and working memory can be improved by training, there is thus far no evidence that children with developmental dyslexia can benefit from working-memory training. In the present study, thirty dyslexic children aged 8-11 years were recruited from an elementary school in Wuhan, China. They received working-memory training including training in visuospatial memory, verbal memory, and central executive tasks. The difficulty of the tasks was adjusted based on the performance of each subject, and the training sessions lasted 40 minutes per day, for 5 weeks. The results showed that working-memory training significantly enhanced performance on the nontrained working memory tasks such as the visuospatial, the verbal domains, and central executive tasks in children with developmental dyslexia. More importantly, the visual rhyming task and reading fluency task were also significantly improved by training. Progress on working memory measures was related to changes in reading skills. These experimental findings indicate that working memory is a pivotal factor in reading development among children with developmental dyslexia, and interventions to improve working memory may help dyslexic children to become more proficient in reading.

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus

A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.

Inter- and intra-hemispheric EEG coherence in patients with mild cognitive impairment at rest and during working memory task

Objective： To assess functional relationship by calculating inter- and intra-hemispheric electroencephalography （EEG） coherence at rest and during a working memory task of patients with mild cognitive impairment （MCI）. Methods： The sample consisted of 69 subjects： 35 patients （n = 17 males, n = 18 females; 52-71 years old） and 34 normal controls （n = 17 males, n = 17 females; 51 -63 years old）. Mini-mental state examination （MMSE） of two groups revealed that the scores of MCI patients did not differ significantly from those of normal controls （P〉0.05）. In EEG recording, subjects were performed at rest and during working memory task. EEG signals from F3-F4, C3-C4, P3-P4, T5-T6 and O1-O2 electrode pairs are resulted from the inter-hemispheric action, and EEG signals from F3-C3, F4-C4, C3-P3, C4-P4, P3-O1, P4-O2, T5-C3, T6-C4, T5-P3 and T6-P4 electrode pairs are resulted from the intra-hemispheric action for delta （1.0-3.5 Hz）, theta （4.0-7.5 Hz）, alpha-1 （8.0-10.0 Hz）, alpha-2 （10.5-13.0 Hz）, beta-1 （13.5-18.0 Hz） and beta-2 （18.5-30.0 Hz） frequency bands. The influence of inter- and intra-hemispheric coherence on EEG activity with eyes closed was examined using fast Fourier transformation from the 16 sampled channels. Results： During working memory tasks, the inter- and intra-hemispheric EEG coherences in all bands were significantly higher in the MCI group in comparison with those in the control group （P〈0.05）. However, there was no significant difference in inter- and intra-hemispheric EEG coherences between two groups at rest. Conclusion： Experimental results comprise evidence that MCI patients have higher degree of functional connectivity between hemispheres and in hemispheres during working condition, It suggests that MCI may be associated with compensatory processes during working memory tasks between hemispheres and in hemispheres. Moreover, failure of normal cortical connections may exist in MCI patients.

A forecasting model for wave heights based on a long short-term memory neural network

To explore new operational forecasting methods of waves,a forecasting model for wave heights at three stations in the Bohai Sea has been developed.This model is based on long short-term memory(LSTM)neural network with sea surface wind and wave heights as training samples.The prediction performance of the model is evaluated,and the error analysis shows that when using the same set of numerically predicted sea surface wind as input,the prediction error produced by the proposed LSTM model at Sta.N01 is 20%,18%and 23%lower than the conventional numerical wave models in terms of the total root mean square error(RMSE),scatter index(SI)and mean absolute error(MAE),respectively.Particularly,for significant wave height in the range of 3–5 m,the prediction accuracy of the LSTM model is improved the most remarkably,with RMSE,SI and MAE all decreasing by 24%.It is also evident that the numbers of hidden neurons,the numbers of buoys used and the time length of training samples all have impact on the prediction accuracy.However,the prediction does not necessary improve with the increase of number of hidden neurons or number of buoys used.The experiment trained by data with the longest time length is found to perform the best overall compared to other experiments with a shorter time length for training.Overall,long short-term memory neural network was proved to be a very promising method for future development and applications in wave forecasting.

Working Memory Function in Chinese Dyslexic Children:A Near-Infrared Spectroscopy Study

The deficiency theories of dyslexia are quite contradictory and the cross-cultural studies in recent years mainly focused on whether the dyslexics among cultures shared the same cognitive profile or just based on the language.This study used Near-Infrared Spectroscopy (NIRS) imaging to measure the regional cerebral blood volume (BV) and the changes of cerebral activation in the left prefrontal cortex of 12 Chinese dyslexic children and their 12 age-matched normal controls during the Paced Vis-ual Serial Addition Test (PVSAT).Results showed that the scores of PVSAT of dyslexic children were significantly lower than those of the normal children (t=3.33,P<0.01).The activations of the left pre-frontal cortex in the normal group were significantly greater than those of dyslexic children (all P<0.01).Our results indicated that Chinese dyslexia had a general deficiency in working memory and this may be caused by the abnormal metabolic activity of brain blood volume in the left prefrontal cortex and the deficits in brain function might be the basis of neuropathology of Chinese dyslexia.Present study sup-ports the difference on brain activation of dyslexics from different languages may be caused by the same cognitive system related to reading.

Low-level lead exposure effects on spatial reference memory and working memory in rats

BACKGROUND： Studies have demonstrated that lead exposure can result in cognitive dysfunction and behavior disorders. However, lead exposure impairments vary under different experimental conditions. OBJECTIVE： To detect changes in spatial learning and memory following low-level lead exposure in rats, in Morris water maze test under the same experimental condition used to analyze lead exposure effects on various memory types and learning processes. DESIGN AND SETTING： The experiment was conducted at the Animal Laboratory, Institute of Psychology, Chinese Academy of Science between February 2005 and March 2006. One-way analysis of variance （ANOVA） and behavioral observations were performed. MATERIALS： Sixteen male, healthy, adult, Sprague Dawley rats were randomized into normal con-trol and lead exposure groups （n = 8）. METHODS： Rats in the normal control group were fed distilled water, and those in the lead exposure group were fed 250 mL of 0.05% lead acetate once per day. At day 28, all rats performed the Morris water maze test, consisting of four phases： space navigation, probe test, working memory test, and visual cue test. MAIN OUTCOME MEASURES： Place navigation in the Morris water maze was used to evaluate spatial learning and memory, probe trials for spatial reference memory, working memory test for spatial working memory, and visual cue test for non-spatial cognitive function. Perkin-Elmer Model 300 Atomic Absorption Spectrometer was utilized to determine blood lead levels in rats. RESULTS： （1） In the working memory test, the time to reach the platform remained unchanged between the control and lead exposure groups （F（1,1） = 0.007, P = 0.935）. A visible decrease in escape latencies was observed in each group （P = 0.028）. However, there was no significant difference between the two groups （F（1,1） = 1.869, P = 0.193）. The working memory probe test demonstrated no change between the two groups in the time spent in the target quadrant during the working memory probe test （F（1,1） = 1.869, P = 0.193）. However, by day 4, differences were observed in the working memory test （P 〈 0.01）. （2） Multivariate repetitive measure and ANOVA in place navigation presented no significant difference between the two groups （F（1,1） = 0.579, P = 0.459）. （3） Spatial probe test demonstrated that the time to reach the platform was significantly different between the two groups （F（1,1） = 4.587, P = 0.048）, and one-way ANOVA showed no significant difference in swimming speed between the two groups （F（1,1） = 1.528, P = 0.237）. （4） In the visual cue test, all rats reached the platform within 15 seconds, with no significant difference （F（1,1） = 0.579, P = 0.459）. （5） During experimentation, all rats increased in body mass, but there was no difference between the two groups （F（1,1） = 0.05, P = 0.943）. At day 28 of 0.05% lead exposure, the blood lead level was 29.72 μg/L in the lead exposure group and 5.86 μg/L in the control group （P 〈 0.01）. CONCLUSION： The present results revealed low-level lead exposure significantly impaired spatial reference memory and spatial working memory, but had no effect on spatial learning.

A real-time prediction method for tunnel boring machine cutter-head torque using bidirectional long short-term memory networks optimized by multi-algorithm

Based on data from the Jilin Water Diversion Tunnels from the Songhua River(China),an improved and real-time prediction method optimized by multi-algorithm for tunnel boring machine(TBM)cutter-head torque is presented.Firstly,a function excluding invalid and abnormal data is established to distinguish TBM operating state,and a feature selection method based on the SelectKBest algorithm is proposed.Accordingly,ten features that are most closely related to the cutter-head torque are selected as input variables,which,in descending order of influence,include the sum of motor torque,cutter-head power,sum of motor power,sum of motor current,advance rate,cutter-head pressure,total thrust force,penetration rate,cutter-head rotational velocity,and field penetration index.Secondly,a real-time cutterhead torque prediction model’s structure is developed,based on the bidirectional long short-term memory(BLSTM)network integrating the dropout algorithm to prevent overfitting.Then,an algorithm to optimize hyperparameters of model based on Bayesian and cross-validation is proposed.Early stopping and checkpoint algorithms are integrated to optimize the training process.Finally,a BLSTMbased real-time cutter-head torque prediction model is developed,which fully utilizes the previous time-series tunneling information.The mean absolute percentage error(MAPE)of the model in the verification section is 7.3%,implying that the presented model is suitable for real-time cutter-head torque prediction.Furthermore,an incremental learning method based on the above base model is introduced to improve the adaptability of the model during the TBM tunneling.Comparison of the prediction performance between the base and incremental learning models in the same tunneling section shows that:(1)the MAPE of the predicted results of the BLSTM-based real-time cutter-head torque prediction model remains below 10%,and both the coefficient of determination(R^(2))and correlation coefficient(r)between measured and predicted values exceed 0.95;and(2)the incremental learning method is suitable for realtime cutter-head torque prediction and can effectively improve the prediction accuracy and generalization capacity of the model during the excavation process.

Navigation jamming signal recognition based on long short-term memory neural networks

This paper introduces the time-frequency analyzed long short-term memory(TF-LSTM) neural network method for jamming signal recognition over the Global Navigation Satellite System(GNSS) receiver. The method introduces the long shortterm memory(LSTM) neural network into the recognition algorithm and combines the time-frequency(TF) analysis for signal preprocessing. Five kinds of navigation jamming signals including white Gaussian noise(WGN), pulse jamming, sweep jamming, audio jamming, and spread spectrum jamming are used as input for training and recognition. Since the signal parameters and quantity are unknown in the actual scenario, this work builds a data set containing multiple kinds and parameters jamming to train the TF-LSTM. The performance of this method is evaluated by simulations and experiments. The method has higher recognition accuracy and better robustness than the existing methods, such as LSTM and the convolutional neural network(CNN).