Traffic flow prediction based on improved deep extreme learning machine by Xiujuan Tian, Shuaihu Wu, Xue Xing, Huanying Liu, Heyao Gao, Chun Chen

“…Abstract A new hybrid prediction model is proposed for short-term traffic flow, which is based on Deep Extreme Learning Machine improved by Sparrow Search Algorithm (SSA-DELM). …”
Get full text

LSAF-LSTM-Based Self-Adaptive Multi-Sensor Fusion for Robust UAV State Estimation in Challenging Environments by Mahammad Irfan, Sagar Dalai, Petar Trslic, James Riordan, Gerard Dooly

Get full text

Electrical Storm Optimization (ESO) Algorithm: Theoretical Foundations, Analysis, and Application to Engineering Problems by Manuel Soto Calvo, Han Soo Lee

Get full text

Rotor Flux Controller for Induction Machines Considering Main Inductance Saturation by Diachenko G.

“…The objective of the study is to develop a law for regulating the coordinates of an electromechanical system, taking into account an energy-efficient algorithm for transferring the system from one operation point to another. …”
Get full text

Improved Butterfly Optimizer-Configured Extreme Learning Machine for Fault Diagnosis by Helong Yu, Kang Yuan, Wenshu Li, Nannan Zhao, Weibin Chen, Changcheng Huang, Huiling Chen, Mingjing Wang

“…The model is mainly based on an improved butterfly optimizer algorithm- (BOA-) optimized kernel extreme learning machine (KELM) model. …”
Get full text

Wearable IoT (w-IoT) artificial intelligence (AI) solution for sustainable smart-healthcare by Gurdeep Singh

“…Machine Learning algorithms for classification with higher F-score or performance metrics adopted are Decision Trees (DT), K-Nearest Neighbours (KNN), XGboost, One-class SVM and Logistic Regression. …”
Get full text

Semi-physical Simulation of Adaptive Cruise Control for Electric Vehicle Based on xPC by DING Xiying, WANG Chunqiang, ZHANG Hongyue, WANG Yanan, LIU Xipeng

“…Furthermore, it was translated into C code and then downloaded to the target model machine for simulating the real vehicle. An embedded computer of DSP2812 was used as the adaptive cruise physical controller of vehicles to swith control algorithm for different working conditions and adjust vehicle speed online, so that the constant speed drive or isometric tracking for front vehicles could be realized. …”
Get full text

The calculation algorithm of oil and gas production enterprise energy efficiency indicators by A. Yu. Arestova, V. N. Ulyanov, M. Yu. Frolov

“…The assessment of energy efficiency indicators will require adaptation of the parameter’s identification method for rotating electrical machines in operating modes. …”
Get full text

An Adaptive Data-Driven Approach to Solve Real-World Vehicle Routing Problems in Logistics by Emir Žunić, Dženana Đonko, Emir Buza

“…The work consists of two basic units: (i) an innovative multistep algorithm for successful and entirely feasible solving of the VRPs in logistics and (ii) an adaptive approach for adjusting and setting up parameters and constants of the proposed algorithm. …”
Get full text

Channel estimation method of massive MIMO-OFDM system based on adaptive compressed sensing by Yiyang HU, Lina QI

“…Massive multiple-input multiple-output (MIMO) is a solution for efficiently providing connection services for a variety of machine equipment in the Internet of things (IoT), and efficient connection services require accurate channel estimation.Aimed at the problems of high pilot overhead and poor performance of normalized mean square error (NMSE) estimation in downlink channel estimation of massive MIMO systems, based on the compressed sensing (CS) theory, the common sparsity of the channel space domain was combined while using the feature of lower sparsity of adjacent time slot differential channel impulse response (CIR), which leaded to a significant reduction in pilot overhead.In the reconstruction algorithm, a two-stage differential estimation algorithm, which divided the channel estimation in consecutive time slots with time correlation into two stages, was proposed and the idea of adaptive compressed sensing was combined to achieve fast and accurate CIR estimate.The simulation results show that the proposed two-stage differential channel estimation algorithm not only has a significant improvement in the estimated NMSE performance and data transmission rate compared to the existing CS-based multiple measurement vector (MMV) algorithm, but also show a certain reduction in runtime complexity.…”
Get full text

Channel estimation method of massive MIMO-OFDM system based on adaptive compressed sensing by Yiyang HU, Lina QI

“…Massive multiple-input multiple-output (MIMO) is a solution for efficiently providing connection services for a variety of machine equipment in the Internet of things (IoT), and efficient connection services require accurate channel estimation.Aimed at the problems of high pilot overhead and poor performance of normalized mean square error (NMSE) estimation in downlink channel estimation of massive MIMO systems, based on the compressed sensing (CS) theory, the common sparsity of the channel space domain was combined while using the feature of lower sparsity of adjacent time slot differential channel impulse response (CIR), which leaded to a significant reduction in pilot overhead.In the reconstruction algorithm, a two-stage differential estimation algorithm, which divided the channel estimation in consecutive time slots with time correlation into two stages, was proposed and the idea of adaptive compressed sensing was combined to achieve fast and accurate CIR estimate.The simulation results show that the proposed two-stage differential channel estimation algorithm not only has a significant improvement in the estimated NMSE performance and data transmission rate compared to the existing CS-based multiple measurement vector (MMV) algorithm, but also show a certain reduction in runtime complexity.…”
Get full text

Enhanced Neutrosophic Set and Machine Learning Approach for Breast Cancer Prediction by Ashika T, Hannah Grace, Nivetha Martin, Florentin Smarandache

“…When trained on the N-dataset instead of traditional datasets, ML algorithms such as Decision Tree (DT), Random Forest (RF), and Adaptive Boosting (AdaBoost) perform better. …”
Get full text

Research on adaptive motion methods of flexible knee joints based on the artificial potential field by LUO Tianhong, LI Chaoyang, MA Xiangyu, FU Qiang, FANG Shangchen

“…ObjectiveConsidering the tracking error of the motion trajectory of the flexible knee joint and the influence of the flexibility on the joint motion, an adaptive impedance control method based on the artificial potential field (APF) was proposed.MethodsThe method took the pneumatic artificial muscle as the power source, and by establishing a kinetic model between the human-machine interaction moment and the knee joint motion angular velocity, the size of the impedance control parameter could be adjusted in real time, so as to realize the following of the motion of the exoskeleton knee joint and the human leg; the control parameter was optimized using the APF concept to enhance the effect of the motion following, and the effectiveness of the algorithm was verified by simulation and test.ResultsThe results show that the proposed APF-based adaptive impedance control method enables the exoskeleton to adaptively track the human motion trajectory and can reduce the error of trajectory tracking, thus improving the suppleness of the flexible knee joint control and enhancing the human-machine synergy of the system.…”
Get full text

Adaptive mechanism-based grey wolf optimizer for feature selection in high-dimensional classification. by Genliang Li, Yaxin Cui, Jingyu Su

“…This approach encompasses a novel nonlinear parameter control strategy to balance exploration and exploitation effectively, thereby preventing the algorithm from converging prematurely. Additionally, an adaptive fitness distance balancing mechanism is proposed to prevent premature convergence and enhance search efficiency by selecting high-potential solutions. …”
Get full text

Integrating Machine Learning and Material Feeding Systems for Competitive Advantage in Manufacturing by Müge Sinem Çağlayan, Aslı Aksoy

“…The research employs six machine learning (ML) algorithms—logistic regression (LR), decision trees (DT), random forest (RF), support vector machines (SVM), K-nearest neighbors (K-NN), and artificial neural networks (ANN)—to develop a multi-class classification model for material feeding system selection. …”
Get full text

TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance by Xuanbai Yu, Olivier Caspary

“…These findings offer new insights to support reliable predictive maintenance in industrial settings and provide a new perspective for future research into active vibration control, where vibration signal analysis, feature extraction, and mathematical modeling play key roles in optimizing control algorithms and enhancing the efficiency of adaptive control systems.…”
Get full text

Deep Q-Networks for Minimizing Total Tardiness on a Single Machine by Kuan Wei Huang, Bertrand M. T. Lin

“…This paper considers the single-machine scheduling problem of total tardiness minimization. …”
Get full text

Burnout Risk Profiles in Psychology Students: An Exploratory Study with Machine Learning by M. Graça Pereira, Martim Santos, Renata Magalhães, Cláudia Rodrigues, Odete Araújo, Dalila Durães

“…The results showed that psychological distress, difficulties in emotional regulation, and sleep quality were positively associated with burnout, while psychological well-being was negatively associated. Using machine learning algorithms, two distinct profiles were found: “Burnout Risk” and “No Risk”. …”
Get full text

Sparse Online Gaussian Process Adaptive Control of Unmanned Aerial Vehicle with Slung Payload by Muhammed Rasit Kartal, Dmitry I. Ignatyev, Argyrios Zolotas

Get full text

A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors by Lei Pang, Yi Li, Ming-Xia Liao, Jia-Gang Qiu, Hui Li, Zhen Wang, Gang Sun

“…The deep sub-domain adaptation network algorithm proposed in this study exhibited the best performance, with a recognition rate of 92.87%. …”
Get full text