Estimation of Forces and Powers in Ergometer and Scull Rowing Based on Long Short-Term Memory Neural Networks by Lorenzo Pitto, Frédéric R. Simon, Geoffrey N. Ertel, Gérome C. Gauchard, Guillaume Mornieux

“…Performing leave-one-out validation showed a significant increase in error, confirming that more subjects are needed in order to develop a tool that could be generalizable to external athletes.…”
Get full text

Machine learning approach for optimizing usability of healthcare websites by Amandeep Kaur, Jaswinder Singh, Satinder Kaur

“…Key metrics such as R-square, Mean Square Error (MSE), Mean Absolute Error (MAE), and Explained Variance Score (EVS) confirmed the model’s predictive accuracy. …”
Get full text

Pavement Deterioration Modeling of the International Roughness Index Based on Fuzzy Logic Approach by Abdualmtalab Ali, Abdalrhman Milad, Hussein ALMufargi, Nur Izzi Md Yusoff

“…The performance evaluation of the analytical models was conducted using several performance indicator metrics, including the coefficient of determination (R2), root mean squared error (RMSE), and mean absolute error (MAE).…”
Get full text

EFL STUDENTS’ PERSPECTIVES ON THE USE OF SMALLTALK2ME TO ENHANCE SPEAKING SKILLS: A STUDY OF UNDERGRADUATE LEARNERS by Fadlan Rambe, Ernita Daulay

“…Employing a qualitative design, the study involved four students from a public institution in North Sumatra, who responded to open-ended questionnaires and participated in semi-structured interviews. Data were analyzed through thematic analysis, which revealed several significant themes: AI tools as scaffolding agents, confidence development in speaking, real-time feedback and error correction, social interaction with technology, and accessibility and flexibility of learning platforms. …”
Get full text

Precise Foot Feature Point Localization and Automatic Parameters Measurement by JI Mian, LIN Yanping, WANG Dongmei, CHEN Li, MA Xin

“…The accuracy, repeatability, and consistency of the measurements are evaluated using mean absolute error (MAE), mean absolute percentage error (MAPE), interclass correlation coefficient (ICC), and Bland-Altman plots. …”
Get full text

The convergence mechanism of Low Earth Orbit enhanced GNSS (LeGNSS) Precise Point Positioning (PPP) by Yanning Zheng, Haibo Ge, Bofeng Li

“…In this article, the convergence mechanism of LEO enhanced GNSS PPP is investigated in terms of theoretical analysis and simulated verification. To show the characteristics of the ambiguities during convergence, eigenvalue decomposition is used to divide the ambiguities into orthogonal components, named geometric-related component, clock-error-related component, and independent component. …”
Get full text

Estimation of Actual Evapotranspiration Distribution in the Huaihe River Upstream Basin Based on the Generalized Complementary Principle by Jiaqi Gao, Miao Qiao, Xinfa Qiu, Yan Zeng, Huanhuan Hua, Xiuzhi Ye, Mustapha Adamu

“…The estimation results of actual evapotranspiration show that the generalized complementary principle model had high estimation precision in this basin, with an average absolute error of 16.64 mm and an average relative error of 2.25%. …”
Get full text

Prediction of old goaf residual subsidence integrating EDS-InSAR with EsLSTM in the Loess Plateau, China by Fei Ma, Fei Ma, Qingbin Zhang, Lichun Sui

“…It also outperformed SVR and traditional LSTM models, with a Mean Absolute Error of 2.2 mm and a Root Mean Square Error of 7.9 mm. …”
Get full text

Hybrid Movie Recommendation System With User Partitioning and Log Likelihood Content Comparison by Yongmao Yang, Kampol Woradit, Kenneth Cosh

“…These innovations are designed to tackle cold-start problems and sparsity issues while compensating for information loss to mitigate errors. Under the premise that our model employs consistent evaluation metrics and datasets, comparative analysis against existing models from related literature demonstrates superior performance. …”
Get full text

Application of Artificial Intelligence using K-Means for Programming Question Assessment by Waliyyudin Waliyyudin, Ichsan Ibrahim

“…Five assessment categories were used as clustering standards: Logic and Algorithm, Data Structures, Object-Oriented Programming (OOP), Implementation, and Error Handling. …”
Get full text

The intensity of geomagnetic storms associated with the interplanetary magnetic field and solar wind parameters during Solar Cycle 24 by Anwar Santoso, Sismanto Sismanto, Rhorom Priyatikanto, Eddy Hartantyo, Dyah R. Martiningrum

“…We end with a regression formula that fits the data, with a coefficient of determination of 0.58, a root mean square error of 21.30 nT, and a mean absolute error of 15.87 nT. …”
Get full text

Arithmetic on Your Phone: A Large Scale Investigation of Simple Additions and Multiplications. by Federico Zimmerman, Diego Shalom, Pablo A Gonzalez, Juan Manuel Garrido, Facundo Alvarez Heduan, Stanislas Dehaene, Mariano Sigman, Andres Rieznik

“…We present the results of a gamified mobile device arithmetic application which allowed us to collect vast amount of data in simple arithmetic operations. Our results confirm and replicate, on a large sample, six of the main principles derived in a long tradition of investigation: size effect, tie effect, size-tie interaction effect, five-effect, RTs and error rates correlation effect, and most common error effect. …”
Get full text

Beyond the Current Curve: A Novel Curve Warning System Considering Subsequent Curve Speed Limits by N. S. Manikandan, Ganesan Kaliyaperumal

“…Our proposed method leverages Google Maps path data and an existing curve detection system to extract curvature information. …”
Get full text

IMPLEMENTATION OF A HYBRID METHOD OF SEARCHING FOR CLOSE OBJECTS, TAKING INTO ACCOUNT THE GENERAL AND ACOUSTIC CHARACTERISTICS by Olga Malyeyeva, Vadym Yesipov, Roman Artiukh, Viktor Kosenko

“…Conclusions: According to the results of testing the system by three methods, we can conclude that the proposed hybrid method was the most effective among the studied recommendation methods with the lowest standard error rate.  In addition, the hybrid method on the principle of double organization solves such problems of existing recommendation methods as excessive similarity of recommendations, potentially small number or no proposals at all by compensating data from one block of data from another.…”
Get full text

Machine learning assisted estimation of total solids content of drilling fluids by B.T. Gunel, Y.D. Pak, A.Ö. Herekeli, S. Gül, B. Kulga, E. Artun

“…Analysis of residuals, their histograms and Q-Q normality plots showed Gaussian distributions with residuals that are scattered around a mean of zero within error ranges of ±1% and ±4%, for training and testing, respectively. …”
Get full text

Detection and segmentation framework for defect detection on multi-layer ceramic capacitors by Hyun-Jae Kim, Sung-Bin Son, Heung-Seon Oh

“…Furthermore, we generated pseudo-defect images using generative adversarial networks to obtain sufficient training data. Experiments demonstrate the effectiveness of our framework, which achieved a defect-detection accuracy of 93.1%, as revealed by an in-depth error analysis.…”
Get full text

Shear Stress-Relative Slip Relationship at Concrete Interfaces by Keun-Hyeok Yang

“…In developing the model, the initial shear cracking stress and relative slip amount at peak stress were formulated from a nonlinear regression analysis using test data for push-off specimens. The shear friction strength was determined from the generalized equations on the basis of the upper-bound theorem of concrete plasticity. …”
Get full text

球面渐开线齿形非圆锥齿轮的设计与分析 by 贾庆祥, 裴玉哲, 高士龙, 高建强

“…According to the principle of geodesic curvature of differential geometry and the forming theory of spherical involute of bevel gears,a method of spherical involute tooth profile design is put forward.First,the equivalent bevel gear of the pitch point is built based on the principle of the geodesic curvature of spherical pitch curve big end.Second,tooth profile of the noncircular bevel gear is built through the spherical involute tooth profile of equivalent bevel gear at this pitch point.Finally,3D modeling is built in CATIA through the coordinate transformation matrix and data calculation,and then motion analysis is carried out.From simulation analysis,this method of designing noncircular bevel gear can realize variable speed ratio transmission,movement error is small and the gear operating is in a smooth and steady manner.The main purpose of designing noncircular bevel gear by this method is promotion and application of generating-line method in processing aspect of noncircular bevel gear with spherical involute tooth profile.…”
Get full text

PatchDetect: Breast Cancer Detection combining Unet-ResNet-50 and Patch Embedding LSTM by Hadj Ahmed Bouarara, kadda benyahia

“…The model's performance was optimized using various hyperparameters, achieving an accuracy of 94%, recall of 93%, precision of 92%, and F-measure of 92% while maintaining a minimal error rate of 6%. The findings emphasize the importance of integrating pre-trained CNNs with sequential analysis via LSTMs for feature-rich and temporal data like mammographic patches. …”
Get full text

Identification of Hazardous Substances in Mail by Terahertz Radiation Based on Voigt and AsLS Fitting Spectral Reconstruction by Tao Li, Yungao Gu, Chao Wang, Yiyang Yao, Ying Zhang, Yajie Guo, Dayong Gu

“…Principal component analysis (PCA) results showed that the reconstructed spectral data were easier to identify and the root mean square error (RMSE) of quantitative analysis was the smallest. …”
Get full text