Detection of multiple pesticide residues on the surface of broccoli based on hyperspectral imaging by GUI Jiangsheng, GU Min, WU Zixian, BAO Xiao’an

“…To increase efficiency of the model and reduce the redundancy of the hyperspectral image, using the principal component analysis (PCA) algorithm and successive projection algorithm (SPA) for feature extraction. …”
Get full text

EFTGAN: Elemental features and transferring corrected data augmentation for the study of high-entropy alloys by Yibo Sun, Cong Hou, Nguyen-Dung Tran, Yuhang Lu, Zimo Li, Ying Chen, Jun Ni

“…This study provides a new algorithm to improve the performance and usability of deep learning with structures as inputs, which is effective and accurate for the prediction and development of materials for small data sets.…”
Get full text

High-confidence assessment of functional impact of human mitochondrial non-synonymous genome variations by APOGEE. by Stefano Castellana, Caterina Fusilli, Gianluigi Mazzoccoli, Tommaso Biagini, Daniele Capocefalo, Massimo Carella, Angelo Luigi Vescovi, Tommaso Mazza

“…Since these tools proved to be rather incongruent, we have designed and implemented APOGEE, a machine-learning algorithm that outperforms all existing prediction methods in estimating the harmfulness of mitochondrial non-synonymous genome variations. …”
Get full text

An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis by Syed Saad Azhar Ali, Muhammad Moinuddin, Kamran Raza, Syed Hasan Adil

“…Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control and time series prediction. In this paper, the learning algorithm of radial basis function neural networks is analyzed in a feedback structure. …”
Get full text

Student employment forecasting model based on random forest and multi-features fusion by Zhenguo Xing, Xiao Wu, Jiangjiang Li

“…Secondly, in order to improve the accuracy of the prediction model, a feature selection model combining principal component analysis and random forest algorithm is used to select the optimal subset from the original features. …”
Get full text

Deep learning, irrigation enhancement, and agricultural economics for ensuring food security in emerging economies by Aktam U. Burkhanov, Elena G. Popkova, Diana R. Galoyan, Tatul M. Mkrtchyan, Bruno S. Sergi

“…Leveraging data from the top 10 countries with the lowest climate index values according to the Numbeo ranking, this article introduces a groundbreaking deep learning algorithm. This algorithm has the potential to revolutionize agricultural productivity and food security in the face of climate change, filling the gap in research on deep learning in agriculture. …”
Get full text

Research on Short-Term Load Forecasting of LSTM Regional Power Grid Based on Multi-Source Parameter Coupling by Bo Li, Yaohua Liao, Siyang Liu, Chao Liu, Zhensheng Wu

“…Traditional short-term power load-forecasting methods have certain limitations in accuracy and stability, especially when dealing with complex weather and voltage changes. To improve the prediction accuracy, this paper proposes a short-term power load-forecasting model of a regional power grid based on multi-source parameter coupling with a long short-term memory neural network (LSTM) and adopts an improved particle swarm optimization (IPSO) algorithm to optimize the LSTM network. …”
Get full text

Evaluation of LSRB Pathfinding Performance in an Autonomous Obstacle-Avoiding Robot by Usran Usran, Muh. Rafly Rasyid, Wawan Firgiawan

“…This study presents an evaluation of the performance of the Left-Straight-Right-Back (LSRB) algorithm implemented in an autonomous obstacle-avoiding robot. …”
Get full text

ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION by O. S. Hilko, S. P. Kundas, V. I. Kovalenko

Get full text

Correlation of Tracks from Different Radars in Information Processing by Attraction Method by U. A. Aparovich, A. V. Shevchenko

Get full text

User Random Access Technology Based on Beam Hopping Satellite Communication System by Zixuan HUANG, Jiaxi ZHOU, Jing ZHANG, Zhengyu ZHANG

“…On the basis of geosynchronous earth orbit multi-beam satellite communication systems, this paper designed the process of user random access to the network and specifi c signaling interaction under the agile beam mechanism, and proposed the scheduling strategy and allocation scheme of the agile signaling beam.This scheme increased the fl exibility of access resource allocation under the premised of ensured that all users could accessed the network, eff ectively improved the utilization rate of satellite network resources.The request of user access to the satellite communication network belongs to the burst type, it is more suitable to use the random competition access, so this paper based on the general random competition access strategy, proposed an adaptive random competition access algorithm based on the heat value, based on the heat value predicted by the network side, the user selects diff erent random access strategies for access.Through the simulation and analysis of the optimization algorithm, it is proved that the algorithm could eff ectively reduced the probability of access collision under various network loads, so as to achieved the purpose of users quickly accessing the network.…”
Get full text

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

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