Challenges in Generating Accurate Text in Images: A Benchmark for Text-to-Image Models on Specialized Content by Zenab Bosheah, Vilmos Bilicki

“…GPT-4 serves as an automated evaluator, assessing outputs based on key metrics such as text accuracy, readability, formatting consistency, visual design, contextual relevance, and error recovery. Weighted scores generated by GPT-4 are compared with human evaluations to measure alignment and reliability. …”
Get full text

A reversible and robust hybrid image steganography framework using radon transform and integer lifting wavelet transform by B. M. El-den, Walid Raslan

“…The system exhibits exceptional robustness, with a Bit Error Rate (BER) as low as 0.0017 under scaling distortions, representing a 30% reduction compared to state-of-the-art methods. …”
Get full text

Inaccurate DNA synthesis in cell extracts of yeast producing active human DNA polymerase iota. by Alena V Makarova, Corinn Grabow, Leonid V Gening, Vyacheslav Z Tarantul, Tahir H Tahirov, Tadayoshi Bessho, Youri I Pavlov

“…The primer/template and composition of the exogenous DNA precursor pool can be adapted to monitor replication fidelity in cell extracts expressing various error-prone Pols or mutator variants of accurate Pols. …”
Get full text

Using fuzzy decision support to create a positive mental health environment for preschoolers by Xinyue Li

“…The FDS process identifies the relationship between a child’s behaviour and attention level with maximum accuracy (97.98%), specificity (96.79%), sensitivity (97.08%), and minimum error (0.28). Behavioural prediction helps improve preschoolers’ mental health and activities effectively. …”
Get full text

A unified electromagnetic framework for light absorption: beyond the Bouguer–Beer–Lambert law by Moses Kayanda Kiteto, Cleophas Achisa Mecha

“…The proposed modification demonstrated outstanding performance, achieving a root mean square error (RMSE) of less than 0.06 for all tested materials and displaying remarkable capabilities far beyond the Bouguer–Beer–Lambert law. …”
Get full text

Strengthening system stability through wind farm integration: a comprehensive study of TCSC with Fuzzy Logic Control by Jawaharlal Bhukya

“…Clinical trial registration: Not applicable.…”
Get full text

Establishment and Experimental Verification of Stress-Temperature Coupled Damage Model of Warm Frozen Soil by Shan Wei, Yang Tao, Guo Ying, Xu Zhichao, Zhang Chengcheng

“…Compared with the prediction results of the single stress damage model, the stress-temperature coupled damage model can effectively reduce the influence of the parameter estimation error on the results and improve the overall stability of the model.…”
Get full text

Path-Loss Optimized Indoor Laser-Based Visible Light Communication System for Variable Link Length Gigabit-Class Communication by Faheem Ahmad, Sathisha Ramachandrapura, Jyothsna Manattayil, Varun Raghunathan

“…Communication experiments with on-off modulated at 1.5 Gbps achieved BER of ∼3 × 10^−3 for the optimized link, which is below the forward-error correction threshold. The above communication performance is achieved at illumination levels at the receiver as low as ∼45 and 16 lx. …”
Get full text

Impulsively-Laser Excitation and Propagation of Ultrasonic Waves through Nanomagnetic Fluid by A. R. Baev, A. I. Мitkovets, M. V. Asadchaya, A. L. Mayorov

“…In the measurement process, the concentration of the dispersed phase in tmagnetic fluid was varied from zero to 8 % and the energy in the impulse – from zero to 10 mJ.For the first time, it was established that: a) an amplitude of the function of the optoacoustic transformation in a magnetic fluid, depending on the concentration of the dispersed phase, has a maximum determined by the fluid physical properties and boundary conditions; b) for all samples within the measurement error, a quasilinear dependence of the specified amplitude of energy in the laser pulse in the range of 0–8 MJ has been established.A number ways of the optoacoustic effects in magnetic fluids to use in ultrasonic testing, measuring the intensity of the laser radiation had been suggested.…”
Get full text

Precise GNSS Positioning with Time-differenced Carrier Phases at Variable Sampling Rates by S. Guo, H. Yang, Y. Gao

“…The test results show that the GNSS-TDCP algorithm can achieve absolute precise positioning, but the positioning error will drift over time. Besides, the research results on the impact of different sampling rates on the positioning performance can help us to select an appropriate sampling rate for GNSS-TDCP system.…”
Get full text

Tribological behavior of PLA reinforced with boron nitride nanoparticles using Taguchi and machine learning approaches by Harishbabu Sundarasetty, Santosh Kumar Sahu

“…The Relative Root Mean Square Error (RRSME) values decisively confirm that Random Forest Regression (23.86 % wear rate and 18.32 % COF) is more accurate than traditional linear regression approaches. …”
Get full text

Development of Novel Soil Salinity Spectral Index Using Remotely Sensed Data: A Case Study on Balod District, Chhattisgarh, India by Deshpande Vaibhav Prakashrao, Ahmad Ishtiyaq, Singh Chandan Kumar

“…This study demonstrates a strong correlation between reflectance values and field EC data with an R2 value of 0.83 and a mean relative error of 10 %. This study provides a reliable geospatial approach for soil salinity evaluation and sustainable land management techniques to improve agricultural productivity in semi-arid, arid regions with varying soil properties and salinity levels.…”
Get full text

Experimental Study on Gas-Solid Heat Transfer Characteristics for the Vertical Waste Heat Recovery Using the Inverse Problem Method by Sizong Zhang, Zhi Wen, Yi Xing, Xunliang Liu, Hui Zhang, Yaxuan Xiong

“…Among them, the minimum value of the mean relative error is 26.81%. It is proved that the previous empirical correlations are no longer applicable, while the predicted value of this work is in good agreement with the measured value with the mean deviation of only 7.61%. …”
Get full text

Forecasting Ionospheric foF2 Using Bidirectional LSTM and Attention Mechanism by Jun Tang, Dengpan Yang, Mingfei Ding

“…The performance of the prediction model is optimal at high latitudes. The root mean square error (RMSE) and correlation coefficient (R) of the BiLSTM‐Attention model are 0.539 MHZ and 0.908 MHz at high latitudes, respectively. …”
Get full text

Predicting CO2 adsorption in KOH-activated biochar using advanced machine learning techniques by Raouf Hassan, Alireza Baghban

“…Their superior performance is evidenced by high R2 values of 0.9235 (SVR) and 0.9327 (CatBoost), coupled with low mean squared error values of 0.2207 (SVR) and 0.1942 (CatBoost). …”
Get full text

Enhancing Weather Target Detection with Non-Uniform Pulse Repetition Time (NPRT) Waveforms by Luyao Sun, Tao Wang

“…The spectral moments estimation (SME) signal-processing algorithm of the NPRT weather echo is designed to calculate the average power, velocity, and spectrum width of the target. A comprehensive error analysis is conducted to ascertain the efficacy of the NPRT processing algorithm under influencing factors. …”
Get full text

Channel Estimation for Mixed-Analog to Digital Converters Architecture in Massive MIMO Architecture Using Approximate Conjugate Gradient Pursuit Algorithm by Yaseen A. Mohammed Obaidi, Anas L. Mahmood

“…It was found that ACGP achieves lower Minimum Mean Squared Error (MMSE) compared to Orthogonal Matching Pursuit (OMP) and Least Square (LS), particularly in low SNR conditions showcasing its robustness and efficiency in signal reconstruction, achieving an average enhancement of 30% to 50% at moderate SNR levels. …”
Get full text

Tracking and climbing behavior recognition of heavy-duty trucks on roadways by Lei Tang, Jingchi Jia, Zongtao Duan, Jingyu Ma, Xin Wang, Weiwei Kong

“…A Kalman filter is first used to distinguish error offsets from random noise and to estimate the distribution of truck elevations for different time intervals. …”
Get full text

A Comparative Study of Machine Learning and Conventional Techniques in Predicting Compressive Strength of Concrete with Eggshell and Glass Powder Additives by Yan Gao, Ruihan Ma

“…Both the ANN and RSM techniques are effective instruments for predicting compressive strength, according to the statistical results, which include mean squared error (MSE), determination coefficient (R²), and adjusted coefficient (R² adj). …”
Get full text

Assessing the potential of polygenic scores to strengthen medical risk prediction models of COVID-19. by Aldo Córdova-Palomera, Csaba Siffel, Chris DeBoever, Emily Wong, Dorothée Diogo, Sandor Szalma

“…Polygenic scores for COVID-19 computed from summary statistics of the Covid19 Host Genetics Initiative displayed significant associations with COVID-19 in the UK Biobank (p-values as low as 3.96e-9, all with R2 under 1%), but were unable to robustly improve predictive performance of the non-genetic factors. However, error analysis of the non-genetic models suggested that affected individuals misclassified by the medical risk factors (predicted low risk but actual high risk) display a small but consistent increase in polygenic scores. …”
Get full text