Classification of Speech Emotion State Based on Feature Map Fusion of TCN and Pretrained CNN Model From Korean Speech Emotion Data by A-Hyeon Jo, Keun-Chang Kwak

“…In the third stage, we perform feature-map fusion using canonical correlation analysis (CCA), stationary wavelet transform (SWT), and fuzzy c-means-based principal component averaging (FCMPCA), respectively. …”
Get full text

GRU-based multi-scenario gait authentication for smartphones by Qi JIANG, Ru FENG, Ruijie ZHANG, Jinhua WANG, Ting CHEN, Fushan WEI

“…At present, most of the gait-based smartphone authentication researches focus on a single controlled scenario without considering the impact of multi-scenario changes on the authentication accuracy.The movement direction of the smartphone and the user changes in different scenarios, and the user’s gait data collected by the orientation-sensitive sensor will be biased accordingly.Therefore, it has become an urgent problem to provide a multi-scenario high-accuracy gait authentication method for smartphones.In addition, the selection of the model training algorithm determines the accuracy and efficiency of gait authentication.The current popular authentication model based on long short-term memory (LSTM) network can achieve high authentication accuracy, but it has many training parameters, large memory footprint, and the training efficiency needs to be improved.In order to solve the above problems a multi-scenario gait authentication scheme for smartphones based on Gate Recurrent Unit (GRU) was proposed.The gait signals were preliminarily denoised by wavelet transform, and the looped gait signals were segmented by an adaptive gait cycle segmentation algorithm.In order to meet the authentication requirements of multi-scenario, the coordinate system transformation method was used to perform direction-independent processing on the gait signals, so as to eliminate the influence of the orientation of the smartphone and the movement of the user on the authentication result.Besides, in order to achieve high-accuracy authentication and efficient model training, GRUs with different architectures and various optimization methods were used to train the gait model.The proposed scheme was experimentally analyzed on publicly available datasets PSR and ZJU-GaitAcc.Compared with the related schemes, the proposed scheme improves the authentication accuracy.Compared with the LSTM-based gait authentication model, the training efficiency of the proposed model is improved by about 20%.…”
Get full text

Research on bearing fault diagnosis based on a multimodal method by Hao Chen, Shengjie Li, Xi Lu, Qiong Zhang, Jixining Zhu, Jiaxin Lu

“…Specifically, the method first employs continuous wavelet transform to generate time-frequency images, capturing local and global features of the signal at different scales. …”
Get full text

Safe havens for Bitcoin and Ethereum: evidence from high-frequency data by Fahad Ali, Muhammad Usman Khurram, Ahmet Sensoy

“…To do so, we employ dynamic conditional correlation (DCC), asymmetric DCC, time-varying parameter vector autoregression-based connectedness measures, dynamic correlation-based hedge and safe-haven regression analyses, portfolio optimization and hedging strategies, time- and frequency-based wavelet coherence, and high-frequency 10-min intraday data from January 1, 2018 to January 31, 2023. …”
Get full text

Part B: Innovative Data Augmentation Approach to Boost Machine Learning for Hydrodynamic Purposes—Computational Efficiency by Hamed Majidiyan, Hossein Enshaei, Damon Howe, Eric Gubesch

“…Wave-induced response time series data from experiments on a spherical model under various wave conditions were analyzed using continuous wavelet transform to extract spectral-temporal features. …”
Get full text

Research on Revenue Insurance Premium Ratemaking of Jujube Based on Copula-Stochastic Optimization Model by Li-Mei Qi, Ruo-Yu Yao, Xing-Zhe Zhang, Yu-Jing Zhang, Xiao-Yin Wang, Jian-Ping Tao, Jia-Ming Zhu

“…In the study, firstly, wavelet analysis method was used to stabilize the jujube yield per unit area and the jujube price from 1997 to 2018 in Aksu region, Xinjiang, China. …”
Get full text

Transient Electromagnetic Data Noise Suppression Method Based on MPA-VMD-SVD by Yuheng Li, Yang Zhang, Jiwei Shen, Xinze Wen, Jianmei Chen, Wanqiang Zhu

“…The proposed method is compared to stacking-averaging, wavelet threshold denoising, SVD, empirical mode decomposition, and unoptimized VMD. …”
Get full text

Evaluation of the DWT-PCA/SVD Recognition Algorithm on Reconstructed Frontal Face Images by Louis Asiedu, Bernard O. Essah, Samuel Iddi, K. Doku-Amponsah, Felix O. Mettle

“…This study assessed the performance of the principal component analysis and singular value decomposition algorithm using discrete wavelet transform (DWT-PCA/SVD) as preprocessing mechanism on the reconstructed face image database. …”
Get full text

Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms by Pinjala N Malleswari, Venkata krishna Odugu, T. J. V. Subrahmanyeswara Rao, T. V. N. L. Aswini

“…This method uses the CWT (Continuous Wavelet Transform) to construct a time-frequency visualization of ECG signals, which are subsequently transformed into RGB images. …”
Get full text

Cardiac sound classification using a hybrid approach: MFCC-based feature fusion and CNN deep features by Mahbubeh Bahreini, Ramin Barati, Abbas Kamali

“…Additionally, Mel-Frequency Cepstral Coefficients of empirical wavelet subbands serve as handcrafted features. Canonical correlation analysis is employed for feature fusion, effectively combining crucial information from both feature types. …”
Get full text

Numerical and Experimental Identification of Seven-Wire Strand Tensions Using Scale Energy Entropy Spectra of Ultrasonic Guided Waves by Ji Qian, Xin Chen, Limin Sun, Guowen Yao, Xu Wang

“…A numerical method was first developed to simulate UGW propagation in a seven-wire strand, employing the wavelet transform to extract UGW time-frequency energy distributions for different loadings. …”
Get full text

Investigating surface loading effect on seasonal crustal deformation observed by GNSS in Hong Kong by Hongli Lv, Xiaoxing He, Shunqiang Hu

“…Finally, we carried out cross wavelet transform (XWT) method to quantitatively express the annual phase relationship between GNSS vertical time series and AHNL deformation. …”
Get full text

Bearing Fault Classification Based on Conditional Random Field by Guofeng Wang, Xiaoliang Feng, Chang Liu

“…And the CRF and HMM models are built respectively to perform fault classification by taking the sub band energy features of wavelet packet decomposition (WPD) as the observation sequences. …”
Get full text

Construction and Analysis of Emotion Computing Model Based on LSTM by Huiping Jiang, Rui Jiao, Zequn Wang, Ting Zhang, Licheng Wu

“…Second, four EEG characteristics were extracted via the wavelet transform (WT) using the LSTM-based sentiment classification network. …”
Get full text

Relationship between green bonds and carbon neutrality: evidence from top five emitting countries’ sectoral CO2 emissions by Ugur Korkut Pata, Mustafa Tevfik Kartal, Zahoor Ahmed, Avik Sinha

“…It examines the daily data of sectoral CO2 emissions of the top five CO2-emitting nations from January 2, 2019 to December 30, 2022 using wavelet transform coherence, quantile-on-quantile regression, Granger causality in quantiles, and quantile regression approaches. …”
Get full text

Photodiagnosis and photodynamic recognition of cervical cancer with SEM and AFM images. by Sevcan Aytaç, Gürkan Özbey

“…Daubechies (db2, db3, db4, and db5), Coiflet (coif5, coif4, coif3, and coif2), Symlet (sym5, sym4, sym3, and sym2), and Biorthogonal (bior1.3, bior2.8, bior1.5, and bior3.3) 16 discrete wavelet transformation families (DWTF) have been applied to AFM and SEM images. …”
Get full text

Analyzing Drought Propagation and Its Influential Factors in the Upper Nan Watershed, Thailand by Muhammad Chrisna Satriagasa, Piyapong Tongdeenok, Naruemol Kaewjampa

“…This study employs an innovative approach to examine the transition from meteorological drought (MD) to hydrological drought (HD) in the Upper Nan Watershed (UNW), Thailand, using the standardized precipitation evapotranspiration index (SPEI) and standardized streamflow index (SSI). Cross-wavelet transform (XWT) and Pearson’s correlation analyses reveal a significant positive correlation between MD and HD, with the drought propagation time (DPT) ranging from 2 to 5 months, notably shorter during the dry season. …”
Get full text

Bearing Fault Diagnosis Based on Collaborative Representation Using Projection Dictionary Pair by Dan Ma, Yixiang Lu, Yushun Zhang, Hua Bao, Xueming Peng

“…The proposed algorithm mainly consists of three components. First, a wavelet transform is employed to extract features, which takes advantage of the observation that vibration signals under different conditions have similar frequency spectra. …”
Get full text

Characteristics of Runoff Variation of Heishui River Basin in the Upper Reach of Minjiang River in Changing Environment by WANG Ning, WANG Wensheng, YU Siyi

“…This paper systematically analyzed the variation characteristics of runoff in the Heishui River Basin,the first tributary on the right bank upstream of Minjiang River,in a changing environment.The variation characteristics of runoff series were studied by using an improved heuristic segmentation algorithm,Mann-Kendall trend test,R/S analysis and wavelet analysis with the runoff data of Shaba hydrological station from 1960 to 2015.The results show the followings:① The abrupt change of annual runoff occurred in 1995.② The annual runoff showed a significant decrease trend with a decreasing rate of 0.32 m³/(s·a) in the past 56 years and may keep the decrease trend in the future.During 1960—1995,the annual runoff showed an insignificant decrease trend with a decreasing rate of 0.12 m³/(s·a),and the period of 1996—2015 witnessed an insignificant increase trend with an increasing rate of 0.80 m³/(s·a).③ Under the influence of environmental changes,the average annual runoff before the change point was larger than that after the point,whereas the inter-annual variation was smaller before the abrupt change.The intra-annual distribution form showed a double-peak curve before 1995 and a single-peak curve after 1995.The intra-annual variation range of runoff was significantly different before and after the change point,which could reduce flood control pressure in the basin but was not conducive to the utilization of water resources in non-flood seasons.④Annual runoff had multi-time-scale variation characteristics.During 1960—2015,the annual runoff had noticeable periods of 6 years,16 years and 28 years.Periods of 7 years and 16 years were found for 1960—1995 and 2 years and 5 years for 1996—2015.…”
Get full text

Development of a Comprehensive Comparison Software for Automated Decision-Making in Impulse Testing of Power Transformers, Including a Review of Practices from Analog to Digital by Welson Bassi

“…Despite advances in digital processing, including analyses on the frequency domain rather than only on time, such as transfer function analysis and coherence functions, and other signal transformations, such as wavelet calculation, interpreting differences in waveform records remains subjective. …”
Get full text