End-to-end neural automatic speech recognition system for low resource languages by Sami Dhahbi, Nasir Saleem, Sami Bourouis, Mouhebeddine Berrima, Elena Verdú

“…Using synthetic speech and data augmentation techniques can enhance E2E-ASR performance for low-resource languages, reducing word error rates (WERs) and character error rates (CERs). …”
Get full text

Implementation of a Low- Cost Multi- IMU by Using Information Form of a Steady State Kalman Filter by A. M. Shahri, R. Rasoulzadeh

“…Results of static test for z-axis show that ARW coefficient reduces to 0.0022°/√s and VRW error isdecreased by %50. Also, dynamic test results show the reduction of the standard deviation of combinedrate signal up to six times compared with a single sensor. …”
Get full text

Temperature-Influenced SOC Estimation of LiFePO₄ Batteries in Hybrid Electric Tractors Based on SAO-LSTM Model by Yiwei Wu, Xiaohui Liu, Jingyun Zhang, Mengnan Liu, Lin Wang, Xiaoxiao Du, Xianghai Yan

“…The proposed SAO-LSTM model demonstrated superior SOC estimation performance compared to traditional ampere-hour integration, achieving a 98.23% error reduction. Evaluation results showed 0.39% and 0.31% decreases in root mean square error and mean absolute error, respectively, confirming the model’s robustness and high estimation accuracy for LiFePO₄ batteries in hybrid electric tractors.…”
Get full text

Robust Photovoltaic Power Forecasting Model Under Complex Meteorological Conditions by Yuxiang Guo, Qiang Han, Tan Li, Huichu Fu, Meng Liang, Siwei Zhang

“…However, traditional PV power forecasting models designed for distributed PV power stations often struggle with accuracy due to unpredictable meteorological variations, data noise, non-stationary signals, and human-induced data collection errors. To effectively mitigate these limitations, this work proposes a dual-stage feature extraction method based on Variational Mode Decomposition (VMD) and Principal Component Analysis (PCA), enhancing multi-scale modeling and noise reduction capabilities. …”
Get full text

Impact of Data Assimilation Frequency and Observation Location in Thermal Effluent Modeling for Coastal Waters by N. Alsulaiman, M. vanReeuwijk, M. D. Piggott

“…The optimal station locations were identified using the ensemble‐based targeted observation method, based on their ability to maximize the reduction of the analysis error variance. …”
Get full text

Enhancing Human–Computer Interaction With Cultural Nuance: A Deep Reinforcement Learning Perspective by Xiaohui Wang

“…The results of the studies show that adding cultural backgrounds to temperament recognition can result in significant gains, as demonstrated by a 4.6% reduction in detection error over previous models. …”
Get full text

Optimal Design of High-Precision Focusing Mechanism Based on Flexible Hinge by Zhanwei Huo, Guangzhen Li, Luyang Tan, Tianwen Yang, Dapeng Tian, Ji Li

“…This study indicates that the inclusion of a flexible hinge in the focusing mechanism leads to a substantial decrease in tilt error.…”
Get full text

Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques by Jie Xu, Lixing Bo

“…The primary objective is to enhance supply chain efficiency and robustness by integrating these AI methods to address common challenges such as demand forecasting, resource allocation, and cost reduction. …”
Get full text

Chronological age estimation from human microbiomes with transformer-based Robust Principal Component Analysis by Tyler Myers, Se Jin Song, Yang Chen, Britta De Pessemier, Lora Khatib, Daniel McDonald, Shi Huang, Richard Gallo, Chris Callewaert, Aki S. Havulinna, Leo Lahti, Guus Roeselers, Manolo Laiola, Sudarshan A. Shetty, Scott T. Kelley, Rob Knight, Andrew Bartko

“…TRPCA improves age prediction accuracy from human microbiome samples, achieving the largest reduction in Mean Absolute Error for WGS skin (MAE: 8.03, 28% reduction) and 16S skin (MAE: 5.09, 14% reduction) samples, compared to conventional approaches. …”
Get full text

A high-precision 1 × 15 infrared temperature measurement linear array based on thermopile sensors by Jindong Bai, Wenhang Yang, Shouzheng Zhu, Haijun Jin, Yuchen Zhang, Ke Jin, Xiaoshuai Liu, Chunlai Li, Jianyu Wang, Hongxing Qi, Shijie Liu

“…On the FPGA control board, a multiparameter temperature compensation algorithm is used to address intrinsic temperature differences and consistency errors among the sensors. Compared with the traditional two-point calibration method, the temperature measurement accuracy of the proposed method reaches 26 mK in the temperature range of 293–303 K, the maximum repeatability error of the sensor is less than 5.5 mK, and the non-uniformity error between 15 sensors is less than 11.9 mK. …”
Get full text

Degradation Diagnosis and Control Strategy for a Diesel Hybrid Powertrain Considering State of Health by Jingxian Tang, Bolan Liu, Wenhao Fan, Dawei Zhong, Liang Liu

“…For combined degradation, the strategy achieved a 12.3% tracing error reduction with 3.7% more energy consumption. …”
Get full text

Efficient Hybrid Deep Learning Model for Battery State of Health Estimation Using Transfer Learning by Jinling Ren, Misheng Cai, Dapai Shi

“…Achieving accurate battery state of health (SOH) estimation is crucial, but existing methods still face many challenges in terms of data quality, computational efficiency, and cross-scenario generalization capabilities. …”
Get full text

Just-in-time updated DBN BOF steel-making soft sensor model based on dense connectivity of key features by Lu Zongxu, Liu Hui, Chen FuGang, Li Heng, Xue XiaoJun

“…Finally, a Just-in-time learning (JITL) method is proposed to reduce the high-dimensional steelmaking data of the BOF while preserving the data structure by using the stream learning dimensionality reduction method to improve the accuracy of the metrics in the JITL process, so that the online fine-tuned model can be applied to the forecasting requirements under different working conditions. …”
Get full text

Task domain independent speech keyword detection system by HAN Jiang, LIU Xiao-xing, YAN Yong-hong, ZHANG Peng-yuan

“…A multiple scale acoustic modeling framework for task-domain independent keyword spotting was proposed.A large-scale phoneme set was obtained automatically through decision-tree based phoneme clustering,and a large-scale phoneme acoustic context dependent background model was trained accordingly through using standard HMM training framework.The modeling accuracy for filler speech is improved.Under the framework,an efficient searching space construction through using shared HMM state was also described.Experimental results showed that in average absolute 6.9% improvement of keyword recognition accuracy could be obtained.Furthermore an acoustic context neighbor algorithm to measure acoustic confidence and a method of computing candidate keyword likelihood based on proposed multiple-scale acoustic model were proposed and a fusing method based on FLDA was adopted.The effectiveness of acoustic confidence measure is improved significantly.Experimental results showed that absolute 3.0% reduction of equal error rate could be obtained.…”
Get full text

Radio frequency fingerprint data augmentation for indoor localization based on diffusion model by Haojun AI, Weike ZENG, Jingjie TAO, Jinying XU, Hanxiao CHANG

“…The radio frequency fingerprint indoor localization method ensures the accuracy by collecting a sufficient amount of fingerprints in the offline state to build a dense fingerprint database.A data augmentation method called FPDiffusion was proposed based on diffusion model to reduce the cost of fingerprint acquisition.Firstly, a temporal graph representation of the fingerprint sequence was constructed, the forward process of the diffusion model was accomplished by adding Gaussian noise, and a U-Net was utilized for the reverse process.The loss function of the network was designed according to the characteristics of radio frequency fingerprints.Finally, the computational process for generating dense fingerprints based on sparse fingerprints was presented.Experimental results demonstrate that FPDiffusion achieves 76% and 28% localization error reduction on K-nearest neighbor (KNN) and convolutional neural network (CNN) respectively, and significantly improves localization accuracy on KNN compared to Gaussian process regression (GPR) and GPR-GAN when only a small amount of labeled fingerprints is available.…”
Get full text

Partial Differential Equations-Based Iterative Denoising Algorithm for Movie Images by Pingli Sun, Chenxia Wang, Min Li, Lanqi Liu

“…Film video noise can usually be defined as the error information visible on the video image, caused by the digital signal system. …”
Get full text

Gait-based Parkinson’s disease diagnosis and severity classification using force sensors and machine learning by Navita, Pooja Mittal, Yogesh Kumar Sharma, Anjani Kumar Rai, Sarita Simaiya, Umesh Kumar Lilhore, Vimal Kumar

“…Parkinson’s disease is the primary neurodegenerative disorder that results in a gradual reduction in motor function. Early detection and monitoring of the disease progression is highly challenging due to the gradual progression of symptoms and the inadequacy of conventional methods in identifying subtle changes in mobility. …”
Get full text

Model based multi-loop predictive control scheme for multivariable processes by Arun Ramaveerapathiran, Muniraj Rathinam, Karuppiah Natarajan, Muthiah Athi, Patil Mounica

“…A model based multi-loop predictive control method is presented. The proposed method directly uses the process model without approximation and reduction. …”
Get full text

THE PROFILE OF CREATIVE THINKING PROCESS: PROSPECTIVE MATHEMATICS TEACHERS by Gunawan Gunawan, Ferry Ferdianto, Fauzi Mulyatna, Reni Untarti

“…Methodology –The applied research method was qualitative with an exploratory approach. …”
Get full text

Research on the application of improved MCMC algorithm in the measurement of high-dimensional financial data by Naijia Liu, Yuchao Su

“…A parallelized Markov chain Monte Carlo algorithm based on wavelet transform is developed to effectively reduce the difficulty of multivariate stochastic fluctuation modeling and Bayesian inference by decomposing the original data with high frequency and filtering noise reduction based on the wavelet theory; secondly, an adaptive process and a multi-chain parallel sampling method are introduced to adjust the sample generating mechanism of the multivariate stochastic fluctuation model. …”
Get full text