Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition by Dan QU, Wen-lin ZHANG

“…Original eigenphone speaker adaptation method performed well when the amount of adaptation data was suffi-cient.However,it suffered from server overfitting when insufficient amount of adaptation data was provided.A sparse group LASSO(SGL) constraint eigenphone speaker adaptation method was proposed.Firstly,the principle of eigenphone speaker adaptation was introduced in case of hidden Markov model-Gaussian mixture model (HMM-GMM) based speech recognition system.Then,a sparse group LASSO was applied to estimation of the eigenphone matrix.The weight of the SGL norm was adjusted to control the complexity of the adaptation model.Finally,an accelerated proximal gradient method was adopted to solve the mathematic optimization.The method was compared with up-to-date norm algorithms.Experiments on an mandarin Chinese continuous speech recognition task show that,the performance of the SGL con-straint eigenphone method can improve remarkably the performance of the system than original eigenphone method,and is also superior to l₁、l₂-norm and elastic net constraint methods.…”
Get full text

A PSO weighted ensemble framework with SMOTE balancing for student dropout prediction in smart education systems by Achin Jain, Arun Kumar Dubey, Shakir Khan, Arvind Panwar, Mohammad Alkhatib, Abdulaziz M Alshahrani

“…This methodology balances the dataset using SMOTE, optimizes model hyperparameters, and fine-tunes ensemble weights through PSO to improve predictive performance. …”
Get full text

Research on Unmanned Aerial Vehicle Path Planning for Carbon Emission Monitoring of Land-Side Heavy Vehicles in Ports by Xincong Wu, Zhanzhu Li, Xiaohua Cao

“…Lastly, this paper focuses on the initial path planning problem of drone monitoring and proposes an improved A* algorithm (IEHA). The algorithm improves the search method of child nodes by eliminating nodes that collide with obstacles, thereby reducing the threat of path collisions. …”
Get full text

Kinematic Calibration of Industrial Robots Based on Distance Information Using a Hybrid Identification Method by Guanbin Gao, Yuan Li, Fei Liu, Shichang Han

“…The singular value decomposition (SVD) is used to eliminate the redundant parameters of the error model. To solve the problem that traditional optimization algorithms are easily affected by data noise in high dimension identification, a novel extended Kalman filter (EKF) and regularized particle filter (RPF) hybrid identification method is presented. …”
Get full text

A Data-Driven Monitoring System for a Prescriptive Maintenance Approach: Supporting Reinforcement Learning Strategies by Joaquín Ordieres-Meré, Antonio Sánchez-Herguedas, Ángel Mena-Nieto

“…The aim of this study was to evaluate machine learning algorithms’ capacity to improve prescriptive maintenance. …”
Get full text

Ensemble Methods for Parameter Estimation of WRF‐Hydro by Arezoo RafieeiNasab, Michael N. Fienen, Nina Omani, Ishita Srivastava, Aubrey L. Dugger

“…Results show a large improvement in the model performance. In summary, our study demonstrates the efficacy of employing iES alongside differential weighting of observations, highlighting its potential to enhance hydrological model parameter estimation.…”
Get full text

Multi-Feature Long Short-Term Memory Facial Recognition for Real-Time Automated Drowsiness Observation of Automobile Drivers with Raspberry Pi 4 by Michael Julius R. Moredo, James Dion S. Celino, Joseph Bryan G. Ibarra

“…Through algorithm optimization, dataset expansion, and the integration of additional features and feedback mechanisms, the model can be improved in terms of performance and reliability.…”
Get full text

Early Warning of Axillary Lymph Node Metastasis in Breast Cancer Patients Using Multi-Omics Signature: A Machine Learning-Based Retrospective Study by Ke Z, Shen L, Shao J

“…The AUC of GLRM was 0.818 (95% CI: 0.757~0.879), significantly lower than that of RFM’s AUC 0.893 (95% CI: 0.836~0.950).Conclusion: The prediction models based on machine learning (ML) algorithms and multiomics have shown good performance in predicting ALN metastasis, and RFM shows greater advantages compared to traditional GLRM. …”
Get full text

Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning by Chunguang Bi, Xinhua Bi, Jinjing Liu, He Chen, Mohan Wang, Helong Yu, Shaozhong Song

“…Subsequently, LF-NMR features and image morphological data were integrated to construct a classification model and the SVM hyperparameters were optimized using an improved differential evolution algorithm, achieving a final classification accuracy of 96.36%, which demonstrated strong robustness and precision. …”
Get full text

Enhancing Crowd Safety at Hajj: Real-Time Detection of Abnormal Behavior Using YOLOv9 by Amani A. Alsabei, Tahani M. Alsubait, Hosam H. Alhakami

“…Leveraging deep learning, this research accurately identifies features of abnormal behavior from the HAJJv2 dataset, specifically curated and annotated for the Hajj context. Optimization of the YOLOv9 algorithm for this scenario demonstrated superior performance metrics (mean Average Precision (mAP@0.5), Recall, and Precision) when compared with its predecessors (YOLOv4, YOLOv5, YOLOv7, and YOLOv8), highlighting significant improvements in detection accuracy and real-time applicability. …”
Get full text

A case study on the application of a data-driven (XGBoost) approach on the environmental and socio-economic perspectives of agricultural groundwater management by Sheng-Wei Wang, Yen-Yu Chen, Shu-Han Hsu, Yu-Hsuan Kao, Masaomi Kimura, Li-chiu Chang, Tzi-Wen Pan, Chuen-Fa Ni

“…This study develops a groundwater level prediction model using the extreme gradient boosting (XGB) algorithm, employing power consumption, precipitation, and groundwater level data as input features. …”
Get full text

Economic sizing and placement of hydrogen fueling and electric vehicles charging stations powered by renewable and battery systems in smart distribution network by Mehdi Veisi

“…The solution is derived using Benders decomposition algorithm to achieve optimal results. The primary innovation highlighted in this paper includes integrating renewable resources and battery systems to power the refueling station, leveraging reactive power control for improved station performance, and addressing both operational and economic objectives in the distribution system. …”
Get full text

Predicting Trip Duration and Distance in Bike-Sharing Systems Using Dynamic Time Warping by Ahmed Ali, Ahmad Salah, Mahmoud Bekhit, Ahmed Fathalla

“…These two contributions of the proposed approach complement existing prediction models for rentals and returns, providing a comprehensive solution for BSS optimization. …”
Get full text

Research on Electric Spot Trading of Electric Vehicles Based on Block Chain by ZHANG Zhening, ZHANG Xinyu, GONG Gangjun

“…Finally,by designing intelligent contract, the optimization process of trading scheme was validated by a genetic algorithm.The simulation results show that through the efficient operation of the smart contract of block chain, the formulation of the optimal trading scheme to meet the objectives of multiple participants is achieved, which can provide a reference for improving the safety, reliability and efficient coordination of the electric vehicle charging market.…”
Get full text

Research on Active–Passive Training Control Strategies for Upper Limb Rehabilitation Robot by Yongming Yang

“…By utilizing neural networks to train sample data during rehabilitation training, the fuzzy rules and membership functions in fuzzy intention recognition algorithm are optimized to improve the accuracy of intention recognition during training. …”
Get full text

Research on ionospheric parameters prediction based on deep learning by Yuntian FENG, Xia WU, Xiong XU, Rongqing ZHANG

“…For ionospheric parameter prediction, the short-term and daily mean value prediction of ionospheric parameters was established by long short-term memory (LSTM) predictive neural network modeling.Two methods of point-by-point prediction and sequence prediction were utilized.Furthermore, in order to predict the hourly and daily changes of ionospheric parameters, the proposed scheme was optimized by multidimensional prediction and empirical mode decomposition (EMD) algorithm.Finally, the feasibility of the proposed optimization algorithm in improving the prediction accuracy of ionospheric parameters is verified.…”
Get full text

Deep coal fluidization mining ropeless hoisting system and its cooperative driving control strategy by Shuai LIU, Jiusheng BAO, Jinhao DAI, Yan YIN, Liang ZHAO, Zhongbin WANG, Shirong GE

“…The research results show that the fuzzy PI loop coupling control algorithm can optimize the motor response characteristics and improve the following and synchronization performance among multiple motors. …”
Get full text

The balance between traffic control and economic development in tourist cities under the context of COVID-19: A case study of Xi'an, China. by Wang Xiang, Zezhi Wang, Xin Pan, Xiaobing Liu, Xuedong Yan, Li Chen

“…Further, the factor traffic control intensity is included in the model. After determining the functional relationship between the control intensity and the number of tourists and the cumulative number of confirmed cases, the NSGA-II algorithm is employed to perform multi-objective optimization with consideration of the requirements for epidemic prevention and control and for economic development to get an appropriate traffic control intensity and suggest scientific traffic control measures. …”
Get full text

Robust collaborative mesh networking with large-scale distributed wireless heterogeneous terminals in industrial cyber-physical systems by Tao Wang, Jun Liu, Lianglun Cheng, Hong Xiao

“…Second, the robustness-aware collaborative mesh networking problem is formulated with a multi-objective optimization model, and an improved multi-objective particle swarm optimization algorithm based on self-adaptive evolutionary learning is exploited to search out the Pareto optimal particles with better distribution and diversity. …”
Get full text

Neuro-fuzzy controller based adaptive control for enhancing the frequency response of two-area power system by M.S. Elborlsy, Samir A. Hamad, Fayez F.M. El-Sousy, R.M. Mostafa, H.E. Keshta, Mohamed A. Ghalib

“…FPI and PI controllers' parameters are optimally tuned using a recent optimization technique known as the Coati Optimization Algorithm (COA). …”
Get full text