Assessing the Effectiveness of DL-Clustering for Energy Optimization in Wireless Sensor Networks by Shailaja S. Halli, Poornima G Patil

“…In order to find the ideal choice for the input, the algorithm classifies system decisions, mobile data collectors, routing, and mobility. …”
Get full text

Realtime Precise Orbit Determination Technology for LEO Mega-Constellation by Zhen LI, Chuang SHI

“…Supported by GNSS, it analyzed the advantages and disadvantages of solving LEO satellite orbit on the ground or onboard the satellites.The high-fidelity non-conservative force models were applied to the real-time orbit determination algorithm.To separate the kinematic and dynamic orbit determination process had been a great advantage for LEO satellites with much frequent orbital maneuvers.The test results showed that the accuracy of accelerations computed from the radiation pressure and atmospheric drag non-conservation force models were around 5 nm/s².Use the broadcast ephemeris, the real-time orbit determination algorithm could get an accuracy of 0.8 m in the satellites′ positions and 1.1 mm/s accuracy in the satellites′ velocity.When the real-time precise ephemeris of GNSS satellites were provided, the algorithm could get an accuracy of 8 cm in the LEO satellites′ position and 0.1 mm/s in the velocity.The method for real-time orbit determination and orbit prediction in this paper could be used to support the construction of navigation system with the mega-constellations.…”
Get full text

Study of model construction of fuel production from waste plastic pyrolysis based on machine learning by CHEN Sihan, YUAN Zhilong, WANG Ye, SUN Yifei*

“…The Gradient Boosting Regression (GBR) algorithm has the best fitting performance for predicting oil yield (R^2=0.91, RMSE=7.78), while the adaptive boosting algorithm (AdaBoost) has the best fitting performance for predicting gas yield (R^2=0.83, RMSE=6.42), enabling accurate prediction of reaction conditions. …”
Get full text

Informative Path Planning Using Physics-Informed Gaussian Processes for Aerial Mapping of 5G Networks by Jonas F. Gruner, Jan Graßhoff, Carlos Castelar Wembers, Kilian Schweppe, Georg Schildbach, Philipp Rostalski

“…Physics-informed mean functions, including a detailed ray-tracing simulation, are integrated into the GP models to enhance the extrapolation performance of the GP prediction. As a central element of the GP prediction, a quantitative evaluation of different mean functions is conducted. …”
Get full text

Harnessing Novel Data‐Driven Techniques for Precise Rainfall–Runoff Modeling by Saad Sh. Sammen, Reza Mohammadpour, Karam AlSafadi, Ali Mokhtar, Shamsuddin Shahid

“…In this study, data‐driven techniques, such as the group method of data handling (GMDH), extreme learning machine (ELM), and two hybrids of artificial neural network (ANN) with Cuckoo search algorithm (ANN + Cuckoo) and genetic algorithm (ANN + GA) were used to model the rainfall–runoff relationship. …”
Get full text

Investigation on the Temperature Distribution of Asphalt Overlay on the Existing Cement Concrete Pavement in Hot-Humid Climate in Southern China by Zuzhong Li, Yayun Zhang, Chunguang Fa, Xiaoming Zou, Haiwei Xie, Huaxin Chen, Rui He

“…This research is to analyze the impact of meteorological factors on temperature at 2 cm depth in asphalt overlay by ReliefF algorithm and also obtain the temperature prediction model using MATLAB. …”
Get full text

PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse by Einari Vaaras, Manu Airaksinen, Okko Rasanen

“…This paper introduces a novel SSL algorithm for time-series data called Prediction of Functionals from Masked Latents (PFML). …”
Get full text

Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning by Jiaze Wu, Hao Liang, Changsong Ding, Xindi Huang, Jianhua Huang, Qinghua Peng

“…We have established a new algorithm with high accuracy to predict BP classification from PPG via matching of CWT type and segment length, which is a promising solution for rapid prediction of BP classification from real-time processing of PPG signal on a wearable device.…”
Get full text

FocusDet: an efficient object detector for small object by Yanli Shi, Yi Jia, Xianhe Zhang

“…SIOU multi-dimension accurately locates the prediction box, and SoftNMS uses the Gaussian algorithm to remove redundant prediction boxes. …”
Get full text

The Sentiment Analysis Reviewing Indosat Services from Twitter Using the Naive Bayes Classifier by Febri Astiko, Achmad Khodar

“…This sentiment analysis uses machine learning to get patterns an model that can be used again to predict new data. …”
Get full text

Height of Hydraulic Fracture Zone Based on PSO_LSSVM Model by Hebin Zhang, Tingting Wang, Bin Wu, Haijun Feng

“…At the same time, this study develops a particle swarm optimization algorithm based on adaptive inertia weight and a least squares support vector machine model to achieve height prediction of water conducting fracture zones. …”
Get full text

Multi-Factor Modeling Method of the Load Sharing Ratio under Moving Train Loads by Yong Liu, Shiyu Zhang, Yang Jin, Yuxiang Song

“…At the same time, a procedure for establishing the LSR multi-factor prediction model is put forward, namely, we (1) determine the LSR function form and the fitting algorithm; (2) perform parameter sensitivity analysis to determine the main influencing parameters of the LSR function; and (3) design a quadratic regression orthogonal test to obtain the prediction formula of the LSR function coefficients. …”
Get full text

Transfer Learning of High-Dimensional Stochastic Frontier Model via Elastic Net by Jiahao Chen, Wenjun Chen, Yunquan Song

“…When the target data is limited, transfer learning improves the accuracy of model estimation and prediction by transferring the source data. When the transferable source is known, a transfer learning algorithm for a high-dimensional stochastic frontier model is proposed based on Elastic Net. …”
Get full text

Analysis method of software failure modes in command information system based on complex networks by WANG Bo, JIANG Xuping, JING Huiqian

“…Based on a weighted undirected connected graph, this paper constructs a static model of the complex network for the command information system software, proposes a hierarchical centrality algorithm for the multi-layer neighbor influence of nodes, realizes the prediction of software network fault sources, and mines the fault propagation path based on the ant colony system algorithm. …”
Get full text

Damage Recovery Method for Air–Sea Cross-Domain Communication Network Based on Improved Dijkstra and Load Balancing by Zhigang Shang, Hongyu Zhang, Jing Yang

“…This paper proposes a link selection strategy based on an improved Dijkstra algorithm and load balancing on the basis of link quality prediction. …”
Get full text

Scalable data assimilation with message passing by Oscar Key, So Takao, Daniel Giles, Marc Peter Deisenroth

“…In combination with a GPU-accelerated implementation, we can scale the algorithm to very large grid sizes while retaining good accuracy and compute and memory requirements.…”
Get full text

Estimation of State of Charge for Lithium-Ion Battery Based on Finite Difference Extended Kalman Filter by Ze Cheng, Jikao Lv, Yanli Liu, Zhihao Yan

“…The results show that the model can essentially predict the dynamic voltage behavior of the lithium-ion battery, and the FDEKF algorithm can maintain good accuracy in the estimation process and has strong robustness against modeling error.…”
Get full text

Using Time Clusters for Following Users’ Shifts in Rating Practices by Dionisis Margaris, Costas Vassilakis

“…In that sense, the practice of using a single mean value for adjusting users’ ratings is inadequate, since it fails to follow such shifts in users’ rating practices, leading to decreased rating prediction accuracy. In this work, we address this issue by using the concept of dynamic averages introduced earlier and we extend earlier work by (1) introducing the concept of rating time clusters and (2) presenting a novel algorithm for calculating dynamic user averages and exploiting them in user-user collaborative, filtering implementations. …”
Get full text

Boosting Barlow Twins Reduced Order Modeling for Machine Learning‐Based Surrogate Models in Multiphase Flow Problems by T. Kadeethum, V. L. S. Silva, P. Salinas, C. C. Pain, H. Yoon

“…To address the challenge of high contrast data in multiphase flow problems due to injection wells and faults, we employ a boosting algorithm within BBT‐ROM. This algorithm sequentially trains a set of weak models (i.e., inaccurate models), improving prediction accuracy through ensemble learning. …”
Get full text

A unique, consistent identifier for alternatively spliced transcript variants. by Alberto Riva, Graziano Pesole

“…The isoform signature uniquely identifies a transcript structure, and can therefore be used as a key in databases of alternatively spliced isoforms, or to compare alternative splicing predictions produced by different methods. In this paper we present the algorithm to generate isoform signatures, we provide some examples of its application, and we describe a web-based resource to generate isoform signatures and use them in database searches.…”
Get full text