Error Level Research Articles

Resource‐Efficient Adaptive Variational Quantum Algorithm for Combinatorial Optimization Problems

AbstractVariational quantum algorithms (VQAs) are quantum‐classical hybrid algorithms that are promising for the near future. The Quantum Approximate Optimization Algorithm (QAOA) is a representative VQA for solving combinatorial optimization problems. However, the parameterized quantum circuit (PQC) of QAOA still has room for improvement. The existing method, called ADAPT‐QAOA, has improved the PQC of QAOA, but the circuit depth remains deep. A Resource‐Efficient Adaptive VQA (RE‐ADAPT‐VQA) that utilizes gates from a new gate pool is proposed to construct a PQC. RE‐ADAPT‐VQA incrementally integrates parameterized quantum gates based on the gradient until the predefined stopping criteria are satisfied, and a rollback mechanism is proposed to ensure that the circuit remains shallow. The algorithm is experimentally simulated to solve Max‐Cut problem and the maximum independent set problem. The results show that RE‐ADAPT‐VQA significantly reduces circuit depth, single‐qubit gates, and CNOT gates compared to existing methods, while maintaining the same level of energy error.

BODY SIZE AS A LEADING INDICATOR OF RUN SIZE AND APPLICATION TO IN-SEASON FORECASTING OF SOCKEYE SALMON IN BRISTOL BAY, ALASKA

Bristol Bay supports the world’s largest fishery for sockeye salmon which are harvested during an extremely condensed time period as fish return to their natal rivers. Uncertainties in pre-season forecasts of run size challenge managers and the fishing community because of limited time to adapt strategies within a season. Pre-season forecast errors from 2000-2023 were as large as 29%, with a mean absolute percent error (MAPE) of 15%. We used autoregressive models including mean size-at-age of returning sockeye salmon, along with other environmental covariates, and weighted these models by the inverse of their MAPE to produce an ensemble in-season model that was subsequently weighted with preseason forecasts. This methodology improved forecasts of run size substantially earlier in the fishing season than currently possible and had an average MAPE of 12% (~6 million fish), approximately one week into the fishing season. This level of error is not met by current in-season methods until approximately 2 weeks later after the season has peaked, and is better than current pre-season methods in most years.

Tomato Stem and Leaf Segmentation and Phenotype Parameter Extraction Based on Improved Red Billed Blue Magpie Optimization Algorithm

In response to the structural changes of tomato seedlings, traditional image techniques are difficult to accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a tomato point cloud stem and leaf segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The framework uses a four-layer Convolutional Neural Network (CNN) for stem and leaf segmentation by incorporating an improved swarm intelligence algorithm with an accuracy of 0.965. Four key phenotypic parameters of the plant were extracted. The phenotypic parameters of plant height, stem thickness, leaf area and leaf inclination were analyzed by comparing the values extracted by manual measurements with the values extracted by the 3D point cloud technique. The results showed that the coefficients of determination (R2) for these parameters were 0.932, 0.741, 0.938 and 0.935, respectively, indicating high correlation. The root mean square error (RMSE) was 0.511, 0.135, 0.989 and 3.628, reflecting the level of error between the measured and extracted values. The absolute percentage errors (APE) were 1.970, 4.299, 4.365 and 5.531, which further quantified the measurement accuracy. In this study, an efficient and adaptive intelligent optimization framework was constructed, which is capable of optimizing data processing strategies to achieve efficient and accurate processing of tomato point cloud data. This study provides a new technical tool for plant phenotyping and helps to improve the intelligent management in agricultural production.

Genetic algorithm optimized BP neural network for fast reconstruction of three-dimensional radiation field.

The three-dimensional radiation field is an important database reflecting the radioactivity distribution in a nuclear facility. It is of great significance to accurately and quickly grasp the radiation dose field distribution to implement radiation protection. Presently, majority of radiation field reconstruction algorithms concentrate on two-dimensional reconstruction and can only measure on a regular grid. With the progress of artificial intelligence technology, neural networks have great potential in radiation field reconstruction. In this work, an improved Genetic Algorithm Optimized Backpropagation (GA-BP) neural network was proposed, which can efficiently reconstruct the radiation dose rate at any given position within the three-dimensional space, even under the condition of a low sampling rate. The proposed method achieves a remarkable speed, capable of reconstructing nearly 500 spots in 0.01s. Two Monte Carlo simulations corresponding to the shielded and unshielded cases verified the effectiveness of the proposed method. The method was further tested on datasets with equally spaced and randomly distributed data points. In both simulation scenarios, the proposed method demonstrated the ability to reconstruct the three-dimensional dose rate field using less than 6% of the data for the simulation cases with a low error level of 3% (unshielded) to 8% (shielded). In the real experimental validation, the error is at 15%, and the point error is less than 30% in most areas.

Analysis of Student Errors in Solving Problems on Three-Dimensional Shapes with Flat Surfaces: A Qualitative Study on Eighth-Grade Students

This study analyzes errors made by eighth-grade students in solving problems involving three-dimensional geometric shapes with flat surfaces and examines the factors causing these errors. Using a qualitative descriptive approach, three students with varying error levels (high, medium, low) were selected for analysis through written tests and in-depth interviews. Data were processed using the Miles and Huberman model: data reduction, data presentation, and conclusion drawing. Findings identified four main error types: factual, conceptual, principle, and operational. High-error students mainly struggled with conceptual understanding and operations, while low-error students primarily made operational errors. The results highlight that weak conceptual understanding and cognitive overload were the key factors in these errors. This study implies that teaching strategies should enhance both conceptual and procedural knowledge, utilizing interactive and manipulative learning methods to reduce cognitive load and improve student performance in geometry.

The impact of physical education and sports lessons on physical activity competence

In this study, it is aimed to compare the Physical Activity (PA) proficiency of 12th-grade students in Bingöl Province who take and do not take Physical Education and Sports (PES) lesson in the 2023-2024 academic years. A total of 231 12th-grade students (105 girls and 126 boys), with an average age of 17.51±0.57 years, height of 169.49±9.42 cm, and weight of 60.05±11.94 kg, participated in the study. Of these students, 149 were enrolled in PES lesson at two different Anadolu high schools, while 82 were not enrolled in PES lesson at two different vocational and technical Anadolu high schools. The Physical Activity Proficiency Scale (PAAS), developed by Campbell et al. in 2016 and adapted into Turkish by Saygın et al. in 2017, was applied to the participants to assess their physical activity proficiency. The obtained data were analyzed using the Mann-Whitney U test. The level of statistical significance (α error level) was accepted as p<0.05. A significant difference in favor of students who take PES lessons was found between the students who take and do not take PES in the second item of the "Physical Activity at School" dimension and the third item of the "Physical Activity in Transportation" dimension (p<0.05). Although no significant differences were found in other dimensions and items, participants who took PES lesson scored higher than their peers who did not take PES. In the data obtained based on gender, no statistically significant difference was found between male students who take and do not take PES lesson. In females, a statistically significant difference was found in favor of participants who take PES lesson in the first, second, third, and sixth items of the "Physical Activity at School" dimension (p<0.05). Based on the data obtained, 12th-grade students who take PES lessons have more confidence in their physical activity proficiency. In conclusion, by encouraging students to engage in physical activity, it can be said that promoting exercise habits in children will not only enhance their academic success but also help them integrate exercise into their lives after their education, leading to a healthier body.

How do manipulation checks interfere with the inference of causal relationships?

This study investigates the performance of mediation analyses, including manipulation check variables, in experimental studies where manipulated psychological attributes are independent variables. We simulated the level of manipulation intensities and measurement errors of the manipulation check variable to test the validity of the analytic practice. Our results showed that when manipulation is successful and measurement error is low, mediation analyses with the manipulation check variable revealed an unstable path coefficient and standard error. Moreover, many of the detected indirect effects were inconsistent mediation situations. However, when individual differences in psychological attributes remained within the condition (low manipulation intensity) and the manipulation check variable contained low measurement error, the indirect effect indicated the validity of the manipulation. We discuss the implications of our findings for the use of manipulation checks in experimental research.

Writing a research proposal for post graduate degree dissertation by a post graduate medical student

Introduction: Research proposal writing is needed a keen interested and knowledge in their speciality. It is very important and essential one for any type of research in science and in any field. Their dissertation work only helps/gives a good solution to know a new–line of treatment. I have discussed about the various steps in research methodology, preparation of a research proposal, how to conduct/proceed a dissertation and how to write a dissertation/study. Materials and Methods: I have discussed I this paper related various steps in research methodology like research topic, research design, target population, sample size and how to calculate it, how to frame inclusion and exclusion criteria, how to enter the data in excel sheet, statistical analysis, what is one sided and two sided tests, how to frame a null and alternative hypothesis, how to conduct/proceed a dissertation and how to write a dissertation/study, What is type-I ad Type-II errors, level of significance, and the process of Scientific Research Committee and Institutional Ethical Committee Approval for a post graduate medical student’s research proposal. Results: All the explanation is to be given in a elaborated ways. The post graduate medical students have to understand easily. Conclusion: From this article, I have concluded that post graduate medical students have to understand and try to follow all the steps of research methodology at the time of their medical degree dissertation proposal preparation.. Adequate minimum calculated sample size should be determined to get a significant results in their studies. Getting SRC ad IEC approval for their dissertation work is a mandatory process in the medical curriculum. Finding the sample size for their PG degree dissertation at the time of preparation of their research proposal. Keywords: post graduate medical student, research methodology, level of significant, type-I and type-II errors, proposal, dissertation

Improvement of the management system of the pharmaceutical service of the health care institution

When providing medical care, harm to patients' health associated with the use of drugs occurs in 10-40% of cases. The issue of ensuring safety in the field of health care is a global problem. The relevance of the problem of improving the quality of pharmaceutical care and estimating the costs of medical care requires research. The purpose of the work is the formation of principles for improving pharmaceutical management in a health care institution by monitoring and analyzing prescription errors at all stages of drug use. The study was conducted on the basis of LLC "Endotechnomed", surgical clinic "Garvis" in the period 01.09.2019-29.02.2024 and was approved by the commission on biomedical ethics. The bibliographic method and retrospective analysis were used. In the study, the level of errors in appointment lists was calculated, their dynamics and relationship with the costs of medical care for the corresponding period were analyzed. The method of increasing the interval was used, and statistical significance was checked using the non-parametric Mann-Whitney test. The non-parametric method of Spearman's rank correlation is used to determine the characteristics of the relationship between the level of errors in appointment lists and the amount of drug costs for one patient. Statistical processing of the results was carried out using the methods of descriptive and analytical statistics using the integrated Jupyter Notebook development environment. A value of p<0.05 was considered statistically significant when testing all statistical hypotheses. The level of errors over 4.5 years significantly (p<0.002) decreased by 78.44% compared to the initial value (from 139.62‰ to 30.10‰), which was at the global level (10%). These indicators confirm the results of research by Chinese scientists, who prove that properly organized work in an inpatient medical institution can reduce the frequency of errors when prescribing drugs from 6.94% to 1.96%. A statistically significant negative rank correlation of average strength was observed between the amount of expenses for medical care of one patient and the level of errors in prescribing medicines for the considered period (r= -0.49; 95% CI (-0.67)–(-0.26); p<0.001), which contradicts the generally accepted notion and, according to the authors, is related to the uniqueness of the situation during the considered period (first the pandemic, then the war). Therefore, it can be concluded that the introduction of new approaches to control the prescription of medicines led to a significant (p<0.002) reduction in the level of errors in appointment lists over 4.5 years by 78.44% compared to the initial value; the higher level of errors in appointment lists corresponds to lower costs for medical care, which is a consequence of the unstable situation on the drug market during the pandemic and the war in Ukraine; the improvement of pharmaceutical service management processes was directed to the following areas of work: planning, control, implementation and functioning of the information system, personnel management, performance evaluation, involvement of interested parties for the formation and implementation of decisions.

Numerical treatment for Darcy–Forchheimer flow of propylene glycol with carbon nanotubes under the impacts of MHD and activation energy

This study is the application of a recurrent neural networks with Bayesian regularization optimizer (RNNs-BRO) to analyze the effect of various physical parameters on fluid velocity, temperature, and mass concentration profiles in the Darcy–Forchheimer flow of propylene glycol mixed with carbon nanotubes model across a stretched cylinder. This model has significant applications in thermal systems such as in heat exchangers, chemical processing, and medical cooling devices. The data-set of the proposed model has been generated with variation of various parameters such as, curvature parameter, inertia coefficient, Hartmann number, porosity parameter, Eckert number, Prandtl number, radiation parameter, activation energy variable, Schmidt number and reaction rate parameter for different scenarios. The refinement of each data-set is processed through RNNs-BRO for attestation of the proposed scheme. The outcomes are provided through graphical interpretation. The increment of curvature parameter results in the acceleration of the velocity profile, while an opposite behavior is noticed for higher values of inertia coefficient, Hartmann number, porosity parameter for single wall carbon nanotubes (SWCNTs) as well as multi wall carbon nanotubes (MWCNTs). The temperature of fluid increases for both SWCNTs and MWCNTs as the curvature parameter, radiation parameter, Eckert number, and Hartmann number are increased. However, an opposite trend is noticed for Prandtl number. The concentration profile is enhanced for higher values of activation energy variable and curvature parameter for both SWCNTs and MWCNTs, whereas opposite trend is observed for reaction rate parameter, and Schmidt number. The effectiveness of scheme is endorsed through various statistical measures like regression index, error histograms, correlation analysis and convergence analysis showing a minimum level of mean square error (E-12 to E-04) for the comprehensive simulation of the proposed model.

Quantitative assessment of a novel method for fluid thermodynamic test simulation in multicomponent systems

This paper presents a quantitative methodology for simulating fluid thermodynamic tests, including constant composition expansion (CCE), differential liberation (DL), and separator tests, within multicomponent systems. The approach combines equilibrium ratios, flash calculations, and the Peng-Robinson equation of state. Utilizing the PVTp (Pressure - Volume - Temperature) package regression procedure enables the calibration of OmegaA and OmegaB values, enhancing accuracy and minimizing error margins in fluid thermodynamic calculations compared to empirical data. Numerical results demonstrate the effectiveness of this method. Bubble point pressure values from observed, software-generated, and calculated data are 2344, 2339, and 2350.42 psia, respectively. Calculated fluid thermodynamic test results closely align with software predictions and exhibit acceptable error levels compared to the measured data. However, discrepancies in the solution gas - oil ratio during the DL test highlight the need for more comprehensive measured data to improve simulation accuracy and reduce error margins. The comparison between the proposed methodology and collected data confirms the effectiveness of integrating equilibrium ratios, flash calculations, and the Peng-Robinson equation of state for precise fluid thermodynamic calculations. This approach offers a quantitative framework for simulating fluid thermodynamic tests, providing insights while reducing reliance on costly laboratory experiments.

Forecasting electricity consumption using the Principal Component Analysis method

Relevance. The need for accurate forecasting of electricity consumption to improve efficiency and reduce costs at industrial enterprises, which leads to increased competitiveness of goods manufactured by the enterprise. Traditional forecasting methods often do not take into account complex interactions between various factors affecting energy consumption and do not provide the necessary forecast accuracy. The principal component analysis method offers a promising prospect – reducing the volume of processed data (dimensionality) without significant loss of information, which simplifies forecast models while maintaining their accuracy. Aim. To develop an accurate and efficient model for forecasting electricity consumption at industrial enterprises using the principal component analysis method. This model is aimed at eliminating the limitations of traditional forecasting approaches by reducing data dimensionality and increasing the accuracy of predictions, which ultimately improves the efficiency of electricity consumption and reduces financial costs, including those due to forecasting errors. Methods. The principal component analysis method, which allows us to reduce the volume of processed data (dimensionality) by transforming a large set of correlated variables into a smaller set of uncorrelated principal components. The study included the following stages: data import and factor analysis, correlation matrix construction, analysis of selected and accumulated variances for each factor, factor loading matrix construction, dimension reduction, development of a mathematical model using linear regression, and forecast installation and validation. Results. The application of the principal component analysis method allowed us to create a model for forecasting electricity consumption. Its application showed that the first principal component explains 69.65% of the total variance, the second component – ​​17.28%, i. e. together they explain almost 87% of the variance. The developed model provides good agreement between the actual and forecast values ​​of electricity consumption in several time intervals with an average error level within the range of +3 to –5%. This indicates the suitability of the model for forecasting electricity consumption, although some discrepancies indicate the need for its further improvement.

Analysis of Students' Mathematical Communication Skills Through Culturally Responsive Teaching and Differentiated Learning Based on Local Wisdom

This study aims to analyze students' mathematical communication skills in solving problems related to measures of central tendency in real-life contexts, focusing on the aspects of drawing, mathematical expression, and written text, as well as types of Newman’s errors. The analysis involved 25 students, with three selected as representatives based on their mathematical communication skill levels. The findings indicate that, on average, students exhibited a low level of errors across the three aspects, with average scores of 7.5 for drawing, 8.0 for mathematical expression, and 8.5 for written text. In the drawing aspect, students were able to present solutions visually well, although minor inaccuracies were noted. In the mathematical expression aspect, students understood the problems but tended to omit explicit solution steps. For the written text aspect, students often provided numerical results without formulating conclusions in sentence form. The main factors causing errors were a lack of habit in writing solution steps and conclusions, as well as a need for improved accuracy. A differentiated learning approach based on local wisdom positively contributed to reducing student error rates. However, strengthening practice in writing solution steps and composing conclusions is necessary to improve students' overall mathematical communication skills.

Flood Mapping Methodologies in Google Earth Engine Using Optical and Radar Data: A Comparative Study

Floods are among the most severe and frequent natural disasters, impacting numerous countries worldwide. This study investigates flood mapping methodologies utilizing Google Earth Engine (GEE) with Sentinel-1, Sentinel-2, and Landsat data, focusing on the January 2021 Tetouan flood in Morocco. Three approaches were assessed: Sentinel-1 thresholding and NDWI (Normalized Difference Water Index) methods applied to Sentinel-2 and Landsat imagery. The analysis revealed flooded areas of 891 hectares (Sentinel-1), 814 hectares (Sentinel-2), and 1237 hectares (Landsat), validated against ArcGIS (Geographic Information System) results estimating 900 hectares. Sentinel-1 demonstrated superior accuracy with only a 9-hectare deviation and proved effective under cloudy conditions. Sentinel-2 provided a balance between spatial resolution and error levels, with moderate commission and omission errors. Landsat detected the largest flood extent but exhibited a slight overestimation. The study emphasizes the advantages of GEE’s cloud-based platform, which significantly reduced processing time, facilitating rapid flood extent mapping. This scalability and efficiency make GEE an invaluable tool for disaster management. The results underline the potential of these methodologies for accurate and timely flood monitoring, enabling informed decision-making in resilience planning and emergency response. Such advancements are critical for mitigating the impacts of flooding and supporting sustainable disaster management strategies in vulnerable regions worldwide.

Immediate Effects of Whole Body Vibration on Proprioception and Upper Extremity Reaction Speed in Young Adult Students.

There is limited information on the immediate effects of whole-body vibration (WBV) on the upper limb. This study aims to determine the immediate effects of WBV on reaction speed and proprioception in young adult students' upper extremities. In total, 62 students participated in the study. WBV was applied to the participants, and its immediate effects on proprioception and upper extremity reaction speed were examined. Participants' proprioception and perception of joint position at 30-60 degrees of shoulder flexion, shoulder abduction, and elbow flexion angles were measured with absolute error degrees. Reaction rates were evaluated with the Ruler-Drop Test and the mobile application SWAY. A decrease was observed in the absolute error level of the participants' joint position perception at 30-60 elbow and shoulder position degrees, measured after immediate WBV application (p <0.05). After the RDT application, a decrease in the length of catching the target was observed (p <0.05). The SWAY test determined that they moved the smartphone in a shorter time (p <0.05). Right and left RDT scores showed that the distance to catch the ruler was significantly lower in male individuals before the application. In comparison, the distance to catch the ruler was lower after the application (right/left p<0.05). The study found that applying WBV improved upper extremity proprioception perception and reaction speed in young adults. This information can guide clinicians in applying WBV to healthy individuals and those with symptoms.

The Relationship between Nutritional Status and Intellectual Intelligence In 4th-5th Grade Students at SD N 219 Inpres Pannambungan, Maros

Nutritional status is a measure of the condition of a person's body, which can be seen from the food consumed and the use of substances in the body. The purpose of this study is to determine the relationship between nutritional status and intellectual intelligence in elementary school children in grades 4-5 at SDN 219 Inpres Pannambungan. In this study, the research design was observational, with a cross-sectional approach using total sampling. This study uses an intellectual intelligence test tool, namely the CFIT (Culture Fair Intelligence Test. Data analysis was carried out using the SPSS application by conducting univariate analysis related to respondent characteristics, independent variables, and dependent variables, then continued by conducting bivariate analysis, namely the Kolmogorov-Smirnov normality test and the Spearman correlation test. The results of this study showed that the correlation value (-2.72) with the probability value or error level (p=0.035) was smaller than the significant standard value (a=0.05). This study concludes that there is a significant relationship between nutritional status and the intellectual intelligence of children of SDN 219 Pannambungan Presidential Instruction Maros Regency.

Prediction of telecommunications market behavior based on LSTM models

The telecommunications services market faces essential challenges in an increasingly flexible and customer-adaptable environment. Research has highlighted that the monopolization of the spectrum by one operator reduces competition and negatively impacts users and the general dynamics of the sector. This article aims to present a proposal to predict the number of users, the level of traffic, and the operators’ income in the telecommunications market using artificial intelligence. Deep Learning (DL) is implemented through a Long-Short Term Memory (LSTM) as a prediction technique. The database used corresponds to the users, revenues, and traffic of 15 network operators obtained from the Communications Regulation Commission of the Republic of Colombia. The ability of LSTMs to handle temporal sequences, long-term dependencies, adaptability to changes, and complex data management makes them an excellent strategy for predicting and forecasting the telecom market. Various works involve LSTM and telecommunications. However, many questions remain in prediction. Various strategies can be proposed, and continued research should focus on providing cognitive engines to address further challenges. MATLAB is used for the design and subsequent implementation. The low Root Mean Squared Error (RMSE) values and the acceptable levels of Mean Absolute Percentage Error (MAPE), especially in an environment characterized by high variability in the number of users, support the conclusion that the implemented model exhibits excellent performance in terms of precision in the prediction process in both open-loop and closed-loop.

Estimation of the LINDA index prediction based on deep learning models

Recognizing the importance of competition analysis in telecommunications markets is essential to improve conditions for users and companies. Several indices in the literature assess competition in these markets, mainly through company concentration. Artificial Intelligence (AI) emerges as an effective solution to process large volumes of data and manually detect patterns that are difficult to identify. This article presents an AI model based on the LINDA indicator to predict whether oligopolies exist. The objective is to offer a valuable tool for analysts and professionals in the sector. The model uses the traffic produced, the reported revenues, and the number of users as input variables. As output parameters of the model, the LINDA index is obtained according to the information reported by the operators, the prediction using Long-Short Term Memory (LSTM) for the input variables, and finally, the prediction of the LINDA index according to the prediction obtained by the LSTM model. The obtained Mean Absolute Percentage Error (MAPE) levels indicate that the proposed strategy can be an effective tool for forecasting the dynamic fluctuations of the communications market.

Improving poultry system in close house cage through advanced HVAC design: A Review of evaporative cooling pads and energy efficiency in broiler cages

Improving the quality and quantity of livestock production can be achieved by creating a comfortable and safe environment for animals. The use of closed-house pens is one of the methods employed to control temperature, humidity, airflow, and the cleanliness of the living space for animals. Close-house pens are equipped with Heating, Ventilation, and Air Conditioning (HVAC), including the combination of an Evaporative Cooling Pad (ECP) and an exhaust fan. The characteristics of the shape and material composition of the ECP components influence pressure drop and the flow pattern entering the room. This research focuses on reviewing papers related to the development of numerical simulation studies of close-house pens and ECP. The design of numerical simulations and the selection of boundary conditions enhance the precision and error level of predicting fluid flow distribution in closed-house cages. In addition to numerical simulations, the application of energy management calculations provides recommendations regarding the combination of HVAC design and environmental control parameters that need to be considered.

Application of spatial metrology models in cell molecular localization and functional prediction

Understanding a protein’s exact cellular location is often essential to understanding its function. Even with the advancements in computer approaches, protein localization prediction indeed faces major obstacles such as interpretability and handling numerous localization sites. In this research, a novel approach, Squirrel Search Optimized Dynamic Visual Geometry Group Network (SSO-DVGG), is proposed to improve protein sub-cellular localization predictions by utilizing spatial metrology models to tackle these problems. With its simplified architecture, SSO-DVGG can explain whether a protein is directed to particular cellular sites, as well as identify important sequence components like sorting motifs or localization signals. This model allows users to select acceptable error levels by providing a confidence estimate for each prediction and highlighting sequence properties that are responsible for localization. This makes the model interpretable. Furthermore, SSO-DVGG uses a probabilistic methodology and integrates a large amount of data from dual-targeted proteins, which enables it to predict multiple localization locations per protein accurately. SSO-DVGG outperforms the best predictors and shows superior capacity to predict multiple localizations when tested on several independent datasets. By providing a clear and accurate understanding of protein distribution and function, this method promotes the application of spatial metrology models in cell molecular localization and functional prediction.