COVID-19 PROJECTIONS ON JAVA AND BALI ISLANDS INVOLVING VACCINATION AND TESTING INTERVENTIONS USING VARI-X MODEL by Riza Andrian Ibrahim, Budi Nurani Ruchjana

“…The mean-absolute-percentage error (MAPE) of the model for the Java and Bali Islands is 5.3027% and 3.0301%, respectively. …”
Get full text

Wearable damaged clothing fabric image recognition system based on image restoration algorithm by Xu Li, Longlin Zhang

“…The results showed that in the COCO dataset, after 250 iterations, the WFR2S algorithm achieved a damage identification accuracy of 95.5 %, a mean absolute error of 0.011, a real-time processing speed of 30 fps, and a resource consumption of 2.4 W. …”
Get full text

CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY by Indah Manfaati Nur, Rifqi Nugrahanto, Fatkhurokhman Fauzi

“…The results of the GARCH-LSTM hybrid model in this study show a Mean Absolute Percentage Error (MAPE) value of 15.69%. The accuracy value is obtained from the division of training data by 80% and testing data by 20%, with the number of neurons as many as three and epochs of 100 using the Adam optimizer. …”
Get full text

Low fluctuation stiffness design method for vibration reduction of helical gears by YOU Zhiwei, GAO Jingtao, LI Haonan

“…The research results provide theoretical support for the vibration reduction design of the gear system.…”
Get full text

Case Study of Urban Stormwater Simulation in Foshan Based on Urban Time-Variant Gain Model by WANG Chao, GONG Siqi, XIAO Yu

“…The prerequisite for urban stormwater simulation and analysis is to accurately grasp urban rainfall-runoff response laws.This paper analyzes the nonlinear response law of rainfall-runoff and builds a TVGM-urban model to simulate and analyze the measured rainfall and storm scenarios designed under different recurrence periods by taking the Baolitongjifu neighborhood in Chancheng District,Foshan as the research object.The results are as follows.There is a power function correlation between rainfall and runoff in the city.The non-linear relationship between maximum rainfall intensity and peak flood flow can be verified by eight selected flood data in the neighborhood with the fitting effect of the power function (R²=0.6207,p<0.05) better than that of the linear relationship (R²=0.5629,p<0.05).Based on the identification of the catchment area and the subsurface classification,the TVGM-urban model is built in the Baolitongjifu neighborhood,and the model accuracy is verified by the measured rainfall and runoff data.Generally,the simulation results ensure that the Nash efficiency coefficient is greater than 0.7,and the simulation error of the water volume and peak value is within 20%,which can well meet the urban stormwater simulation requirements.The results can provide support and references for analyzing urban rainfall and runoff response laws and studying urban stormwater simulation.…”
Get full text

Augmentation of Semantic Processes for Deep Learning Applications by Maximilian Hoffmann, Lukas Malburg, Ralph Bergmann

“…The results indicate a large potential with a reduction of the prediction error of up to 53%.…”
Get full text

A study on phonemes recognition method for Mandarin pronunciation based on improved Zipformer-RNN-T(Pruned) modeling. by Zhaohui Du, Xiaofeng Zhao, Lin Li, Baohua Yu, Lijiang Miao

“…The experimental results demonstrate that the method performs excellently in the phoneme recognition task, achieving a Word Error Rate (WER) of 1.92% (Dev) and 2.12% (Test) on the AISHELL1-PHONEME dataset, and 4.28% (Dev) and 4.51% (Test) on the ST-CMDS-PHONEME dataset. …”
Get full text

Performance Test of Openflow Agent on Openflow Software-Based Mikrotik RB750 Switch by Rikie Kartadie

“…An operator is responsible for running configuration either to manage rules or application applied in the network. Human error may occur when device configuration run manually by operator. …”
Get full text

Low-Power and Reliable Communications for UWB-Based Wireless Monitoring Sensor Networks in Underground Mine Tunnels by Mohamad Abou El-Nasr, Heba Shaban

Get full text

Random Forest versus Support Vector Machine Models’ Applicability for Predicting Beam Shear Strength by Hayder Riyadh Mohammed Mohammed, Sumarni Ismail

“…In the quantitative term, the minimal root mean square error value was attained (RMSE = 89.68 kN).…”
Get full text

Analysis of the burdens of caregivers providing care to people living with HIV/AIDS in Botswana by N.O. Ama, E.S. Seloilwe

“…Methods: The sample size calculator programme that allows for 95% confidence (and an error margin of 4%) was used: the estimated sample size for the study was 272. …”
Get full text

Textual Data Selection For Language Modelling In The Scope Of Automatic Speech Recognition by Freha Mezzoudj, David Langois, Denis Jouvet

Get full text

A Data-Driven Approach for Urban Heat Island Predictions: Rethinking the Evaluation Metrics and Data Preprocessing by Berk Kıvılcım, Patrick Erik Bradley

“…After the model training, the prediction results are not simply evaluated with most widely used shallow metrics like the Mean Square Error (MSE), but thanks to the raster format of input and output results, some image similarity metrics such as Structural Similarity Index Measure (SSIM) and Learned Perceptual Image Patch Similarity (LPIPS) that are able to detect and consider spatial relations are used during the evaluation and interpretation process, because of their higher usefulness in mimicking human visual judgements. …”
Get full text

Offline Signature Biometric Verification with Length Normalization using Convolution Neural Network by Zahraa Mazin Alkattan, Ghada Mohammad Tahir Aldabagh

“…This is referred to as intra-user variability. This research aims to improve the recognition accuracy of the offline signature. …”
Get full text

Environmental Governance and Green Energy: An Administrative Toolkit to Reduce Environmental Degradation by Muhammad Sajjad Hussain, Muhammad Atif Nawaz, Tusawar Iftikhar Ahmad, Muhammad Azhar Bhatti

Get full text

Finite Element Modeling Of Saint-Venant Equations For Shatt-Al Hilla by Basim Sh. Abed, Hamid H. Hussain, Khalid A. Abdul-Razzaq

“…High accuracy and good agreement were achieved, and minimum Root Mean Square Error (RMSE) of 0.029 was gained for the obtained results compared with the corresponding field observations. …”
Get full text

Optimizing Photovoltaic Power Prediction Using Computational Methods and Artificial Neural Networks by Cempaka Amalin Mahadzir, Ahmad Fateh Mohamad Nor, Siti Amely Jumaat, Noor Syahirah Ahmad Safawi

“…By comparing the Mean Squared Error (MSE) of four different values of derating factor due to dirt which are 0.8, 0.88, 0.9 and 0.98 in ANN predictions comprehend with 4 input layers and 10 hidden layers. …”
Get full text

Graph-Attention Diffusion for Enhanced Multivariate Time-Series Anomaly Detection by Vadim Lanko, Ilya Makarov

“…Recently, among the unsupervised methods, diffusion models have attracted increased attention among researchers for addressing this particular task. However, spatial information often remains underutilized or overlooked in existing models. …”
Get full text

Building a Cybersecurity Culture in Higher Education: Proposing a Cybersecurity Awareness Paradigm by Reismary Armas, Hamed Taherdoost

“…Today, the world is experiencing constant technological evolution, allowing cyberattacks to manifest through different vectors and widely impacting victims, from specific users to serious damage to institutions’ integrity. Research has shown that a significant percentage of recorded cyber incidents are attributed to social engineering practices or human error. …”
Get full text

Modeling Bus Passenger Flow Dynamics Using the Cell Transmission Model for Real-Time Congestion Management by Ala Alobeidyeen

“…This research develops the BUS-CTM, a novel mathematical simulation model that adapts the cell transmission model (CTM) to analyze spatiotemporal passenger flow dynamics in urban bus networks. …”
Get full text