Sum Of Squares Research Articles

Assessment of Combining Ability and Heterosis for Seed Yield and its Attributes in Sunflower (Helianthus annuus L.)

The present study employed three lines and fifteen testers to assess the combining ability and standard heterosis of forty-five hybrids developed through a line × tester mating design. The analysis of variance for combining ability revealed significant variation in the mean sum of squares of parents, testers and the interaction between lines and testers regarding seed yield per plant and its related traits. Among the parents, testers GMU 498 and RHA 378 exhibited superior performance for seed yield/plant. In the hybrids, COSF 6A×CSFI 1862, HA 89A×GMU 1000 and HA 89A×RHA 378 demonstrated significantly better seed yield per plant compared to the checks. The variance for specific combining ability (SCA) exceeded that for general combining ability (GCA), indicating that all traits were governed by non-additive gene action. Among the lines, COSF 12A was identified as a good general combiner for yield-contributing traits, while the testers CSFI 1862, GMU 1000 and GMU 498 were recognized as good general combiners for seed yield per plant. Five hybrids, namely HA 89A × RHA 378, HA 89A × GMU 1000, COSF 12A × CSFI 1855, COSF 6A × CSFI 1862 and COSF 12A × GMU 311, exhibited significantly positive SCA for seed yield per plant. Heterosis over the standard checks (DRSH 1, COH 3 and GK 2002) was estimated and the hybrids HA 89A × GMU 1000 and COSF 6A × CSFI 1862 showed positive significant heterosis for seed yield per plant and related traits. The promising hybrids HA 89A × GMU 1000, HA 89A × RHA 378 and COSF 6A × CSFI 1862 were selected based on their mean performance, SCA effects and standard heterosis for seed yield per plant and its attributes.

A Research on Defects and Improvements to Multi-Armed Slots

In recent years, various large language models have sprung up, which are constantly being trained and updated. Most of the time, these models can provide answers more accurately. However, in some specific cases, the answers generated by training on a large corpus of non-emotion text may not be correct. This paper proposes a feasible method to reduce the sum of squares as much as possible so that the fitting function is closer to the true value. By adding the concept of emotion to deep learning, combined with the fusion model of multi-layer linear regression and neural network learning, it was found that adding emotion is more helpful to the language model through multiple trainings, so that the "arm" pulled by the AI each time gets a larger expectation than the original, which significantly improves the reliability and provides a new idea and direction for the problem in this direction.

Unravelling genetic variability for yield and contributing characteristics in green gram [vigna radiata (L.) wilczek] germplasm

Mungbean [Vigna radiata (L.) Wilczek] is an essential crop for food, feed, and income generation in rice-based farming systems across Southeast Asia and other regions. Its popularity stems from its good taste, high nutritional value, and ease of digestion, making it a promising crop for enhancing livelihoods. However, despite its significance, mungbean productivity remains low, primarily due to environmental stresses and a lack of sufficient genetic variability. This study examines the variability, heritability, phenotypic and genotypic coefficient of variation, and genetic advance among yield-contributing traits in green gram germplasm. A total of 450 germplasm lines were evaluated alongside check varieties, revealing significant variation, with the analysis of variance showing notable differences across nearly all traits. The mean sum of squares for the germplasm was highly significant for all phenotypic traits. Several traits exhibited high estimates of heritability and genetic advance, viz., the number of branches/ plants, number of clusters/ plants, number of pods/ clusters, pod length, test weight, and seed yield/plant, indicating their potential for direct selection in breeding programs. These findings suggest that additive gene effects play a dominant role in controlling these traits, with minimal environmental influence, making simple phenotypic selection an effective approach. The results provide valuable insights for advancing green gram breeding programs focused on improving yield and quality through targeted hybridization and trait selection.

Utilizing VSWIR spectroscopy for macronutrient and micronutrient profiling in winter wheat.

This study explores the use of leaf-level visible-to-shortwave infrared (VSWIR) reflectance observations and partial least squares regression (PLSR) to predict foliar concentrations of macronutrients (nitrogen, phosphorus, potassium, calcium, magnesium, and sulfur), micronutrients (boron, copper, iron, manganese, zinc, molybdenum, aluminum, and sodium), and moisture content in winter wheat. A total of 360 fresh wheat leaf samples were collected from a wheat breeding population over two growing seasons. These leaf samples were used to collect VSWIR reflectance observations across a spectral range spanning 350 to 2,500 nm. These samples were then processed for nutrient composition to allow for the examination of the ability of reflectance to accurately model diverse chemical components in wheat foliage. Models for each nutrient were developed using a rigorous cross-validation methodology in conjunction with three distinct component selection methods to explore the trade-offs between model complexity and performance in the final models. We examined absolute minimum predicted residual error sum of squares (PRESS), backward iteration over PRESS, and Van der Voet's randomized t-test as component selection methods. In addition to contrasting component selection methods for each leaf trait, the importance of spectral regions through variable importance in projection scores was also examined. In general, the backward iteration method provided strong model performance while reducing model complexity relative to the other selection methods, yielding R 2 [relative percent difference (RPD), root mean squared error (RMSE)] values in the validation dataset of 0.84 (2.45, 6.91), 0.75 (1.97, 18.67), 0.78 (2.13, 16.49), 0.66 (1.71, 17.13), 0.68 (1.75, 14.51), 0.66 (1.72, 12.29), and 0.84 (2.46, 2.20) for nitrogen, calcium, magnesium, sulfur, iron, zinc, and moisture content on a wet basis, respectively. These model results demonstrate that VSWIR reflectance in combination with modern statistical modeling techniques provides a powerful high throughput method for the quantification of a wide range of foliar nutrient contents in wheat crops. This work has the potential to advance rapid, precise, and nondestructive field assessments of nutrient contents and deficiencies for precision agricultural management and to advance breeding program assessments.

Using floristic data to shed light on the origin of flora in the poorly studied common cypress habitats of Northern Iran

Despite the ecological importance, there is a large knowledge gap on different habitat types of the Hyrcanian World Heritage. The Hyrcanian Common Cypress Habitats (HCCHs), the easternmost part of the Common Cypress habitats in the world, are one of these habitat types. HCCHs are understudied and threatened by a variety of anthropogenic disturbances. In the current study, synthesizing the floristic data of all HCCHs, we compared the species composition of HCCHs to 20 habitats from the Hyrcanian, Irano-Turanian, and Mediterranean regions. Also, we candidate the HCCH with the highest conservation priority by calculating the phylogenetic richness of HCCHs. The ordination analysis results showed that the HCCHs form a distinct group from the three regions. Thus, we found that the HCCHs have a unique floristic composition. The geographical distance had a weak effect on the grouping (Procrustes Sum of Squares = 0.886 and p-value < 0.001). We also detected that the phylogenetic richness of the HCCHs is highest in the Golestan National Park which is the easternmost habitat of HCCHs. Therefore, this park had the most conservation value. Our results provide new insights into the floristic composition and conservation status of the Hyrcanian World Heritage. We conclude that the bioclimatic classifications might be a better predictor of floristic compositions than biogeographical classifications. Based on the observation of Hyrcanian habitats with intermediate floristic composition, it is necessary to reconsider the biogeographical classifications of the region. Our findings are useful for developing management strategies for HCCHs.

Theory and applications of the sum-of-squares technique

Abstract The sum-of-squares (SOS) approximation method is a technique used in optimization problems to derive lower bounds on the optimal value of an objective function. By representing the objective function as a sum of squares in a feature space, the SOS method transforms non-convex global optimization problems into solvable semidefinite programs. This note presents an overview of the SOS method. We start with its application in finite-dimensional feature spaces and, subsequently, we extend it to infinite-dimensional feature spaces using reproducing kernels (k-SOS). Additionally, we highlight the utilization of SOS for estimating some relevant quantities in information theory, including the log-partition function.

Chemoselective modification of chitosan with arginine and hydroxyproline: Development of antibacterial composite films for wound healing applications

This study explored the enhancement of chitosan for wound dressing applications through selective functionalization with arginine and hydroxyproline amino acids, combined with polyvinyl pyrrolidone (PVP) and polyvinyl alcohol (PVA) in composite films. The research employed chemoselective amino acid grafting followed by solution casting to fabricate the composite materials. Fourier transform infrared (FTIR) analysis verified successful chitosan modification through the presence of a carbamate bond at 1719 cm−1 and an amide bond shift from 1660 to 1680 cm−1, with nuclear magnetic resonance (NMR) analysis providing additional confirmation. The composite films demonstrated exceptional properties, achieving maximum tensile strength of approximately 55 MPa and swelling ratio of about 400 %. Statistical analysis revealed significant variations in mechanical and swelling properties across formulations (p < 0.05), with analysis of variance (ANOVA) showing a between-group sum of squares of 122,980.519 for tensile strength and 352,306.333 for swelling. Duncan's multiple range test identified distinct groupings for tensile strength (5.67–119.67 MPa) and swelling ratios (320.33–565.33 %), demonstrating the impact of composition on material properties. Thermal stability analysis (25–600 °C) revealed a multi-step degradation process, confirming successful modification and composite formation. The amino acid-modified chitosan composites showed remarkable antibacterial enhancement, exhibiting 60 % greater activity against both Gram-positive and Gram-negative bacteria compared to unmodified chitosan. These findings demonstrate the potential of selectively functionalized chitosan composite films for advanced wound dressing applications, combining enhanced antibacterial efficacy with robust mechanical and thermal properties. Future research directions include formulation optimization and in vivo validation of clinical efficacy.

Research on Factors Influencing Housing Price based on Principle Component Analysis and Polynomial Regression

Housing price is influenced by natural, social, economic and other factors. Only by understanding and conducting specific research on these influencing factors can people grasp the laws of housing price movements. Focusing on this issue, this paper chooses the average unit housing prices and their influencing factors of 11 cities in Zhejiang Province in 2022 as the research objects, then establishes a model reflecting the quantitative relationship between housing price and influencing factors. Firstly, relevant data is collected from official websites, including housing prices and 10 main influencing factor indicators of above cities. Secondly, principal component analysis is used for data preprocessing, and five prominent indicators are selected by calculating the relative contribution rate of each factor. Then, by drawing functional images and solving correlation coefficients, a qualitative analysis is conducted on the basic algebraic structure of the regression model. The results indicate that all independent variables include independent terms and cross-terms. Subsequently, through polynomial regression, data matrices for both dependent variable and independent variables are set to solve the coefficients of constant term, linear terms, quadratic independent terms and quadratic cross-terms respectively. Therefore, a model of factors influencing housing price is established. Finally, residuals sum of squares, mean square error, regression sum of squares and determination coefficient are calculated in sequence for the regression model. It turns out that all the statistics are within the ideal range, indicating high precision of data fitting and verifying the accuracy and reliability of the model.

PERFORMANCE AND STABILITY FOR GRAIN YIELD AND YIELD COMPONENTS OF SIX-ROW BARLEY CULTIVARS UNDER VARIOUS ENVIRONMENTS IN KURDISTAN REGION-IRAQ

This study was aimed to investigate yield and yield components of barley (Hordeum vulgare L.) under six different environmental conditions E1- E6 including two sowing date S1 and S2 at three location (Qlyasan, Kanipanka, Chamchamal) in KIR using 10 barley cultivars (C), Numar, Rafidain, Al-warka, Al-Amal, IPPA 265, IPPA 99, Arivat (local), Samir, Qalay 1, and Ukraine (Common cultivated). Experiment was applied using to complete randomized blocks design. The stability analysis was done using the linear regression model. The differences between the means were compared through Duncan multiple range test. The results was revealed that the mean sum of squares due to cultivars, environment, and C x E were highly significant for all studied characters. The cultivar Numar which had highest mean grain yield (3.559) th-1, high bi value1.96 and low S2di 0.058) considered optimal yield stability cultivar. The combination C1E3 gave the top grain yielding (6.91 th-1) due to very high GS, high NS and good TGW performances.

CONSTRUCTION OF A THREE LEVEL SPLIT-LOT DESIGNS IN SUDOKU SQUARE DESIGN STRUCTURE

In this research, a situation where blocking is required for a split lot design in order to tease out noise from the dependent variable (prevent factors other than that of interest influencing the outcome) was considered. Blocking for every stage of the design is administered, an elaborate construction procedure for the design was developed by infusing the ordinary split-lot design into a Sudoku Square design structure, the hybridisation gave it a convenient structure for the research. The linear model and the sum of squares of the design were derived, the ANOVA table was constructed and the table was used to analyse the whole system. The clear advantage of this design has been observed to be the additional source of variation, because the introduction of the Block Sum of Squares will reduce the Error Sum of Squares as a result makes it more efficient, but the fact that precision and cost are both functions of the number of sublots per step as well as the total number of items, comparison is complicated. The new design provides greater precision for main effects.

Design, synthesis, and evaluation of a pyrazole-based corrosion inhibitor: a computational and experimental study

By employing a synergistic blend of experimental and theoretical methodologies, we investigated the corrosion inhibition efficacy of a synthesized pyrazole derivative (BM-01) in a solution of hydrochloric acid (1 M). We utilized molecular dynamics (MD) simulations, scanning electron microscopy (SEM), density functional theory (DFT), complexation, plus electrochemical impedance spectroscopy (EIS). We conducted weight loss (WL) measurements from 298 to 328 K. Inhibition efficacy reached a maximum at a BM-01 concentration of 10−3 M, achieving 90.0% (EIS), 90.40% (WL), and 90.38% (potentiodynamic polarization (PDP)). SEM unveiled the shielding of the carbon-steel surface from acid-induced damage by BM-01. The Langmuir adsorption isotherm exhibited a robust fit with a low sum of squares, standard deviation, and a high correlation coefficient. PDP findings indicated that BM-01 acted as a mixed-type inhibitor, predominantly favoring the cathodic process, suggesting potential corrosion-mitigation properties. Theoretical analyses involving DFT, MD simulations, and radial distribution function were conducted to postulate a mechanism and identify an inhibitory layer. Theoretical outcomes aligned closely with experimental data, thereby reinforcing the validity of our findings.

Genotype × environment interaction and stability analysis of advanced field pea (Pisum sativum L.) genotypes in Southeastern Ethiopia

Field pea is a leguminous crops that have a significant economic contributions to sustainable Ethiopian agriculture. The experiment was conducted at four location in 2015/16 to 2016/17 main cropping seasons with the objectives of to determine the magnitude of genotype by environment interactions and its stability of thirteen field pea genotypes using randomized complete block design with four replications. The AMMI analysis revealed that significant (p<0.01) differences between genotypes, environments and genotype by environment interactions for grain yield. This indicates the genotypes responded differently across environments. The highest mean grain yield was recorded from genotype G12 which records (2992 kg ha−1) followed by genotype G4 2974 kg ha−1 across environments. The AMMI analysis showed that genotypes, environments and there interaction accounted about 72.9 %, 1.2 % and 5.7 % of the total sum of squares respectively. The GGE biplot first two principal components explained about 57.42 % of the total sum square of GEI. The GGE biplot revealed that G4 and G12 were the most stable and high yielding genotypes, while G10 and G9 were the lowest yielder and stable genotypes. The results indicated that genotypes responded differently to environmental conditions and the environments influenced genotype performances.

Combining Ability and Gene Action for Grain Yield and Attributing Traits in Maize (Zea mays L.) Subjected to Drought Stress

Background: Maize production is subdued by many impediments that cause yield minimization. Among various biotic and abiotic stress factors, one significant cause of yield reduction in maize is drought stress. Methods: A set of 15 inbreds which were crossed with 3 narrow base testers in line × tester mating design, and resulting 45 F1s along with the parent inbreds and 3 commercial checks were then, in RCBD, subjected to drought stressed and well-watered conditions to assess their genetic worth during spring 2021. Result: The ANOVA unraveled significant mean sum of squares due to lines, testers and line × tester in pooled analysis for all the ten traits. The inbred EI-2188-2 followed by EI-2448 and EI-03-3 contained fair per se performance and significant high GCA effects over the environments for grain yield/plant, proline content and cob length whereas the cross EI-2448-1 × EI-2156 was found most promising hybrid with significant and high SCA effects across the environments regarding grain yield/plant, proline content and cob girth. Prevalence of non-additive type of genetic variance in governing most of the traits suggests adoption of heterosis breeding will be rewarding for improving yield and drought tolerance. Heterotic pooling of the highlighted inbreds and utilization of the superlative hybrids in further breeding programmes for drought tolerance is proposed.

The role of the O2O blended teaching model in improving the teaching effectiveness of physical education classes

Abstract The deep fusion of Internet technology and education is constantly pushing forward the reform of university education. Traditional educational ideas, concepts, and models cannot keep pace with the times, and hybrid teaching has become a new way of education in colleges and universities. To improve the teaching effect of physical education classes, the study used a blended teaching model and designed a teaching evaluation and performance prediction model under the blended teaching model based on an improved cluster analysis method and attention mechanism. The lab results indicated that under the blended teaching model, students’ performance increased by 12.89 points, and the level of skill mastery and proficiency increased by 26.52 and 28.55%, respectively, with grades more inclined to high score distribution. “Excellent” grade clustering increased by 77.71%, and “Good” grade clustering increased by 19.01%. The minimum error sum of squares of the improved clustering algorithm was 58.18 and 36.25% lower than the other two algorithms, and the clustering results were more relevant. The two-way attention mechanism algorithm predicted higher accuracy results and performed best on all four evaluation metrics, with a prediction accuracy of 98.23%, an accuracy of 98.42%, and an F1 value of 91.78%. This hybrid teaching model is more in line with the characteristics of the physical education teaching discipline, successfully cultivates students’ independent learning ability, stimulates students’ love for physical education courses, and achieves better teaching results.

Genotype by Environment Interaction Using AMMI, GGE Biplot and Multivariate Analysis of Nepalese Aromatic Rice Landraces

Aromatic group of rice comprises fine, medium, long and extra-long grain that has rich in agro-biodiversity, carries historical and cultural significance in Nepalese society. The objective was to identify stable, high-yielding aromatic rice landraces for Nepal Thirty aromatic rice landraces including two released varieties as standard checks were evaluated at three locations during 2020 and 2021. The experiment was laid out in a Randomized Complete Block Design with three replications. The combined analysis of variance indicated differences among genotypes and genotype-environment interactions for grain yield. The additive main effects and multiplicative interaction (AMMI) analysis revealed that genotypic effects for 69%, genotype × environment interaction effects for 28% and environmental effects accounted for 3% of the total sum of squares. Similarly, GGE biplot analysis showed that the principal components (PC1 and PC2) accounted for 53% and 47% of the GGE sum of squares, respectively. Based on AMMI1, AMMI2 biplots, and GGE biplots, the genotypes Samba Masuli Sub-1 and Sugandhit Dhan-1 were identified as the high yielding and stable fine and aromatic rice landraces. Other promising genotypes are Damari Dhan, Tilki, Hiupuri, Kalo Basmati, Gouriya, and Brahmamusi Dhan. Specifically, Samba Masuli Sub-1 demonstrated the highest grain yield performance at the NRRP, Hardinath, while Sunaulo Sugandha and Balamsari Dhan excelled in the Tarahara and Khajura environments, respectively. In PCA analysis, four PCs showed significant eigen value &gt;1.0 contributing more than 84% of total variance. Biplot analysis reflected that 1000 grain weight, panicle length, heading and maturity days, and grain yield showed greater variation among the landraces. The results provide a robust basis for the further evaluation and verification of this findings in advance stage trials. The superior and outstanding landraces with higher yields and aroma are potential future varieties that can be either use directly as varieties after selection or utilize in future breeding programs for the development of new aromatic rice varieties.

Multi-Fractional Gradient Descent: A Novel Approach to Gradient Descent for Robust Linear Regression

Authors: This work introduces a novel gradient descent method by generalizing the fractional gradient descent (FGD) such that instead of the same fractional order for all variables, we assign different fractional orders to each variable depending on its characteristics and its relation to other variables. We name this method Multi-Fractional Gradient Descent (MFGD) and by using it in linear regression for minimizing loss function (residual sum of square) and apply it on four financial time series data and also tuning their hyperparameters, we can observe that unlike GD and FGD, MFGD is robust to multicollinearity in the data and also can detect the real information in it and obtain considerable lower error.

On nonnegative invariant quartics in type A

The equivariant nonnegativity versus sums of squares question has been solved for any infinite series of essential reflection groups but type A. As a first step to a classification, we analyse An-invariant quartics. We prove that the cones of invariant sums of squares and nonnegative forms are equal if and only if the number of variables is at most 3 or odd.

Anomaly Detection in Time Series Data

This paper presents a novel unsupervised approach for anomaly detection in marine diesel engines using a Transformer Neural Network based autoencoder (TAE) and residual analysis with Sequential Probability Ratio Test (SPRT) and Sum of Squares of Normalized Residuals (SSNR). This approach adeptly captures temporal dependencies within normal time-series data without the necessity for labeled failure data. To assess the performance of the proposed methodology, a dataset containing faulty data is generated under the same operational profile as the normal training data. The model undergoes training using normal data, after which the faulty data is reconstructed utilizing the trained model. Subsequently, SPRT and SSNR are used to analyze the residuals from the observed and reconstructed faulty data. Significant deviations surpassing a predefined threshold are identified as anomalous behavior. Additionally, this study explores various architectures of Transformer neural networks and other types of neural networks to conduct a comprehensive comparative analysis of the performance of the proposed approach. Insights and recommendations derived from the performance analysis are also presented, offering valuable information for potential users to leverage. The experimental results demonstrate that the proposed approach can accurately and efficiently detect anomalies in marine diesel engines. Therefore, this approach can be considered as a promising solution for early anomaly detection, leading to timely maintenance and repair, and preventing costly downtime. Also, avoid accidents with probability severe consequences.

Genetic Variability and Character Association in F3 Generation of Chickpea (Cicer arietinum L.) under Rainfed and Irrigated Conditions

The goal of the current study was to analyze the genetic variability and character association in F3 generations of chickpea under rainfed and irrigated conditions to finalize appropriate selection criteria for improvement of seed yield in chickpea under irrigated and rainfed conditions. Five F3 generations of chickpea crosses were evaluated in compact family block design with three replications at Research Farm, ARSS, Hanumangarh, Rajasthan, India. In analysis of variance, mean sum of squares indicated significant differences among the generations for all the characters under both conditions. The highest range of variation was observed for seed yield per plant followed by fruiting branches per plant, pods per plant, 100 seed weight and seeds per pod in irrigated condition, whereas in rainfed condition the highest range of variation was registered by seed yield per plant followed by biological yield per plant, 100 seed weight and pods per plant. The RSG-895 x RSG-888 showed high GCV and PCV for fruiting branches per plant, pods per plant, biological yield per plant, and seed yield per plant in both conditions, as well as for seeds per pod under irrigated condition. Under irrigated condition high value of GCV and PCV were noted in IPC-94-94 x RSG-888 for harvest and in CSJD-901 x RSG-931 for pods per plant, seeds per pod and seed yield per plant. Under rainfed high GCV and PCV were observed in cross RSG-888 x ICC-4958 for seeds per pod. This indicates the existence of wide variability for these traits in the progenies of particular crosses and scope of improvement through simple selection. High heritability coupled with high genetic advance as percentage of mean (GAM) was noted in RSG-888 x ICC-4958 for pod per plant under both conditions. Under irrigated condition, the cross CSJD-901 x RSG-931 for pods per plant, RSG-895 x RSG-888 for seed yield per plant, RSG-888 x ICC-4958 for harvest index, RSG-888 x ICC-4958 and CSJD-901 x RSG-931 for 100-seed weight showed high heritability along with high GAM. Whereas under rainfed, the crosses RSG-895 x RSG-888 and IPC-94-94 x RSG-888 for pods per plant, BG-362 x RSG-931 for seed yield per plant, and IPC-94-94 x RSG-888 for harvest index, demonstrated high heritability along with high GAM. This result indicates the importance of additive gene action in inheritance of these characters, hence simple selection can be used to improve seed yield. Seed yield per plant exhibited positive and significant correlation with fruiting branches per plant, pods per plant, biological yield per plant, harvest index and 100-seed weight under both irrigated and rainfed conditions. In irrigated condition seed yield per plant had significant and positive correlation with days to 50% flowering, days to maturity and plant height, whereas in rainfed condition it had significant and positive association with protein content. Further, inter se these characters were also significantly positively correlated. So, selection based on these characters is expected to bring improvement in the seed yield.

A framework in three different project stages to predict ground-borne noise of trains in railway tunnels

Trains passing through tunnels cause noise and vibrations that negatively affect nearby residents. Developing a model to effectively predict ground-borne noise in nearby buildings faces challenges in the early project phases due to limited available data. This study suggests a framework for three stages based on precision and available information: location stage, planning stage, and construction stage. The first two stages correspond to determining the location and designing the railway track. The third stage involves the construction of the railway tunnel where more detailed information may be acquired by measurements on site. The prediction model presented here is formulated as a source term and correction terms considering train type, track type, track treatment, train speed, distance attenuation, foundation coupling, and floor-to-floor attenuation. Moreover, instead of using safety factors, which may cause unnecessary increase in project costs, the concept of combined uncertainty is applied here, using the estimated standard deviation of each term and the root sum of squares. Consequently, a comprehensive ground-borne noise prediction model adapted to various stages and handling uncertainties is proposed.