Particle Filter Tracking without Dynamics by Jaime Ortegon-Aguilar, Eduardo Bayro-Corrochano

“…In this paper, an alternative to address people tracking is presented. The proposed algorithm is based in particle filters, but instead of using a dynamical model, it uses background subtraction to predict future locations of particles. …”
Get full text

Reconstruction of Wing Structure Deformation Based on Particle Swarm Optimization Ridge Regression by Xinyi Wu, Zhiwei Xu, Jie Zeng

“…To improve the precision, the PSO algorithm is used to optimize the ridge regression parameters and comparative analysis is carried out with the typical structural deformation reconstruction algorithm, such as the KO theoretical method. …”
Get full text

Analysis on waypoint-segment routing and performance evaluation for LEO satellite networks by Xin ZHAO, Guang ZHAO, Rui CHEN, Wennai WANG

“…A waypoint-segment routing (WSR) algorithm was proposed.Based on the predictable periodicity of the topological changes of satellite network, the location of satellite waypoints based on the link state of satellite nodes at the current moment was determined by WSR algorithm.The mechanism of flexible planning of packet transmission paths was responded by segment routing to changes in satellite network topology in advance, and a packet transmission path that was not affected by network topology snapshot switch was calculated.Simulation experiment was based on the NS-3, and the optimized link state routing (OLSR) algorithm and the shortest path algorithm were selected to compare with WSR in order to analyze the delay jitter and packet loss rate.It was proved that compared with OLSR, the maximum delay jitter of WSR was reduced by 46 ms and 126 ms respectively in the two scenarios, the packet loss rate was reduced by 30% and 21% respectively, and the problem of packet transmission path interruption caused by topology snapshot switching can be solved.…”
Get full text

Diagnostics and Prognostics of Boilers in Power Plant Based on Data-Driven and Machine Learning by Achmad Widodo, Toni Prahasto, Mochamad Soleh, Herry Nugraha

“…The proposed method utilizes machine learning techniques through support vector machine (SVM) and random forest algorithm (RFA) for anomaly detection and similarity-based method of dynamic time warping (DTW) for RUL prediction. …”
Get full text

Integer linear programming for unsupervised training set selection in molecular machine learning by Matthieu Haeberle, Puck van Gerwen, Ruben Laplaza, Ksenia R Briling, Jan Weinreich, Friedrich Eisenbrand, Clémence Corminboeuf

“…Within the context of physics-inspired machine learning (ML) applied to chemistry, we demonstrate the relevance of an ILP formulation to select molecular training sets for predictions of size-extensive properties. We show that our algorithm outperforms existing unsupervised training set selection approaches, especially when predicting properties of molecules larger than those present in the training set. …”
Get full text

Elastic Momentum-Enhanced Adaptive Hybrid Method for Short-Term Load Forecasting by Wenting Zhao, Haoran Xu, Peng Chen, Juan Zhang, Jing Li, Tingting Cai

“…The particle swarm optimization (PSO) algorithm is improved by adjusting its elastic momentum, and the enhanced APSO algorithm is employed to optimize the adaptive weights of the hybrid model. …”
Get full text

Optimization of Rituximab Therapy in Adult Patients With PLA2R1-Associated Membranous Nephropathy With Artificial Intelligence by Alexandre Destere, Maxime Teisseyre, Diane Merino, Marion Cremoni, Alexandre O Gérard, Thomas Crepin, Noémie Jourde-Chiche, Daisy Graça, Kévin Zorzi, Céline Fernandez, Vesna Brglez, Sylvia Benzaken, Vincent L.M. Esnault, Sylvain Benito, Milou-Daniel Drici, Barbara Seitz-Polski

“…We developed a machine learning algorithm to predict the risk of underdosing based on patients’ characteristics at rituximab infusion. …”
Get full text

Optimisation of Crystallisation Recipe for Varied Cloud Points Characteristics in Palm Oil Fractions by John Ting Zhi Zhang, Jeng Shiun Lim

“…The artificial neural network (ANN), which uses the Levenberg-Marquardt algorithm, serves as an internal model for predicting process output, whereas the genetic algorithm (GA) investigates a wide range of recipe combinations to maximise yield. …”
Get full text

A data-driven group retrosynthesis planning model inspired by neurosymbolic programming by Xuefeng Zhang, Haowei Lin, Muhan Zhang, Yuan Zhou, Jianzhu Ma

“…Inspired by human learning, our algorithm, akin to neurosymbolic programming, builds upon commonly used multi-step concepts such as cascade and complementary reactions and can evolve from practical experiences, enhancing the prediction model for fundamental and compositional reaction templates. …”
Get full text

Perceived age estimation from facial image and demographic data in young and middle-aged South Korean adults by Ilkoo Ahn, Younghwa Baek, Bok-Nam Seo, Su Eun Lim, Kyoungsik Jung, Ho Seok Kim, Jeongkyun Kim, Sukyung Lee, Siwoo Lee

“…Thus, this study aimed to propose a novel perceived age estimation algorithm to meet the need for an objective method to predict perceived age. …”
Get full text

Time-varying channel estimation in reconfigurable intelligent surface assisted communication system by Kai SHAO, Ben LU, Guangyu WANG

“…Aiming at the key problems need to be solved, such as cascade channel sparse representation, time-varying channel parameter tracking and signal reconstruction, for time-varying cascade channels estimation of reconfigurable intelligent surface (RIS) assisted communication system, a Khatri-Rao and hierarchical Bayesian Kalman filter (KR-HBKF) algorithm was proposed.Firstly, the Khatri-Rao product and Kronecker product transformations were used to obtain the sparse representation of RIS cascaded channels based on the sparse characteristics of channels, thus the RIS cascaded channel estimation problem was transformed into a low-dimensional sparse signal recovery problem.Then, according to the state evolution model of RIS cascaded channel, the time correlation parameter was introduced into the prediction model of HBKF algorithm, and the improved HBKF was applied to solve the problem of time-varying channel parameter tracking and signal reconstruction for completing the time-varying cascaded channels estimation.The sparsity and time correlation of the channel were comprehensively considered in the KR-HBKF algorithm, thus better estimation accuracy could be obtained with small pilot overhead.Compared with the traditional compressed sensing algorithm, the simulation results show that the proposed algorithm has about 5 dB estimated performance improvement, and better robustness performance under different time-varying channel conditions.…”
Get full text

Tracking maneuver target using interacting multiple model-square root cubature Kalman filter based on range rate measurement by Hongqiang Liu, Zhongliang Zhou, Haiyan Yang

“…Their approximate distribution functions are obtained by the use of the expectation maximization algorithm with Gaussian mixture model. Then the probability distribution and probability distribution of measurement prediction residual are combined into a new likelihood function to improve the efficiency of updating the model probability. …”
Get full text

A Reinforcement Learning-Based Generative Approach for Event Temporal Relation Extraction by Zhonghua Wu, Wenzhong Yang, Meng Zhang, Fuyuan Wei, Xinfang Liu

“…To bridge the gap between the optimization objective and task performance metrics, we employ the REINFORCE algorithm to optimize our generative model, designing a novel reward function to simultaneously capture the accuracy of temporal prediction and the quality of generation. …”
Get full text

A Hybrid Deep Learning–Based Feature Selection Approach for Supporting Early Detection of Long-Term Behavioral Outcomes in Survivors of Cancer: Cross-Sectional Study by Tracy Huang, Chun-Kit Ngan, Yin Ting Cheung, Madelyn Marcotte, Benjamin Cabrera

“…ObjectiveThis study aimed to create a new feature selection algorithm to improve the performance of machine learning classifiers to predict negative long-term behavioral outcomes in survivors of cancer. …”
Get full text

Analisis Seleksi Atribut Dalam Memprediksi Kegagalan Skripsi Mahasiswa Menggunakan Algoritme Naïve Bayes pada Jurusan Sistem Informasi Universitas Brawijaya by Satrio Hadi Wijoyo, Satrio Agung Wicaksono, Admaja Dwi Herlambang

“…The highest accuracy is the Naive Bayes algorithm using data training which shows the results of 412 correct predictions with an accuracy of 82.4% and 88 false predictions with a presentation of 17.6%. …”
Get full text

A new method for surge arrester placement in high‐voltage substations considering environmental effects by Faridoddin Safaei, Mohsen Niasati

“…Simulations are based on experimental results, and the number of calculations significantly decreases using the proposed algorithm. Simulations of the sample network and implementation of the proposed algorithm with MATLAB and EMTP‐RV prove the efficiency of the proposed method for optimum SA placement.…”
Get full text

IoT-based personal thermal comfort control for livable environment by Miao Zang, Zhiqiang Xing, Yingqi Tan

“…In the prediction stage, we introduce the cuckoo search algorithm, which converges rapidly, to solve the air temperature and air velocity with the learnt thermal comfort level. …”
Get full text

Peningkatan Akurasi Klasifikasi Algoritma C 4.5 Menggunakan Teknik Bagging pada Diagnosis Penyakit Jantung by Erwin Prasetyo, Budi Prasetiyo

“…The purpose of the authors conducting this research is to determine the application of bagging techniques on the C4.5 algorithm, determine the accuracy of the results in the C4.5 algorithm, and compare the level of accuracy of the application of bagging techniques on the C4.5 algorithm. …”
Get full text

Approximation-Aware Training for Efficient Neural Network Inference on MRAM Based CiM Architecture by Hemkant Nehete, Sandeep Soni, Tharun Kumar Reddy Bollu, Balasubramanian Raman, Brajesh Kumar Kaushik

“…This architecture includes a mapping algorithm that modulates inputs and map AFC to crossbar arrays directly, eliminating the need to predict approximated weights for evaluating output. …”
Get full text

Viscous Flow and Dynamic Stall Effects on Vertical-Axis Wind Turbines by A. Allet, I. Paraschivoiu

“…The numerical procedure used here, based on the control volume approach, is the widely known “SIMPLER” algorithm. The resulting algebraic equations are solved by the TriDiagonal Matrix Algorithm (TDMA) in the r- and z-directions and the Cyclic TDMA in the 0-direction. …”
Get full text