What Information on Volatile Organic Compounds Can Be Obtained from the Data of a Single Measurement Site Through the Use of Artificial Intelligence?

Stanišić, Svetlana; Perišić, Mirjana; Jovanović, Gordana; Maletic, D.; Vudragović, D.; Vranić, Ana; Stojić, Andreja

doi:10.1007/978-3-030-72711-6_12

Cited by 4 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have presented an innovative methodology for the temporal and spatial characterization of toxic substances known as BTEX. Utilizing receptor-oriented air circulation modeling and AI techniques, they have demonstrated the possibility of extracting valuable information from a single measurement point [6].…”

Section: Related Workmentioning

confidence: 99%

Improving Tuberculosis Diagnosis using Explainable Artificial Intelligence in Medical Imaging

Özkurt

2024

Journal of Mathematical Sciences and Modelling

View full text Add to dashboard Cite

The integration of artificial intelligence (AI) applications in the healthcare sector is ushering in a significant transformation, particularly in developing more effective strategies for early diagnosis and treatment of contagious diseases like tuberculosis. Tuberculosis, a global public health challenge, demands swift interventions to prevent its spread. While deep learning and image processing techniques show potential in extracting meaningful insights from complex radiological images, their accuracy is often scrutinized due to a lack of explainability. This research navigates the intersection of AI and tuberculosis diagnosis by focusing on explainable artificial intelligence (XAI). A meticulously designed deep learning model for tuberculosis detection is introduced alongside an exploration of XAI to unravel complex decisions. The core belief is that XAI, by elucidating diagnostic decision rationale, enhances the reliability of AI in clinical settings. Emphasizing the pivotal role of XAI in tuberculosis diagnosis, this study aims to impact future research and practical implementations, fostering the adoption of AI-driven disease diagnosis methodologies for global health improvement.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Tuberculosis Diagnosis using Explainable Artificial Intelligence in Medical Imaging

Özkurt

2024

Journal of Mathematical Sciences and Modelling

View full text Add to dashboard Cite

show abstract

“…The XGBoost model's experimental results have been evaluated by a set of traditional machine learning metrics, including mean squared error (MSE) defined by Equation (10), root mean squared error (RMSE) obtainable by Equation (11), mean absolute error (MAE) calculated by Equation ( 13), and the coefficient of determination (R2) described with Equation (13).…”

Section: Dataset Preprocessing Implementation Technology and Evaluati...mentioning

confidence: 99%

“…In this study, based on our previous research [8][9][10][11][12][13][14][15], we have applied a novel approach based on the XGBoost model to identify the factors which are mostly associated with the observed B[a]P concentrations and the environmental conditions which support and facilitate B[a]P level dynamics and its interactions with other polluting species. The XGBoost itself is an efficient model; nevertheless, its hyperparameters require tuning for each particular prediction task in order to achieve good performance on the observed dataset.…”

Section: Introductionmentioning

confidence: 99%

Potential of Coupling Metaheuristics-Optimized-XGBoost and SHAP in Revealing PAHs Environmental Fate

Jovanović

Perišić

Bačanin

et al. 2023

Toxics

View full text Add to dashboard Cite

Polycyclic aromatic hydrocarbons (PAHs) refer to a group of several hundred compounds, among which 16 are identified as priority pollutants, due to their adverse health effects, frequency of occurrence, and potential for human exposure. This study is focused on benzo(a)pyrene, being considered an indicator of exposure to a PAH carcinogenic mixture. For this purpose, we have applied the XGBoost model to a two-year database of pollutant concentrations and meteorological parameters, with the aim to identify the factors which were mostly associated with the observed benzo(a)pyrene concentrations and to describe types of environments that supported the interactions between benzo(a)pyrene and other polluting species. The pollutant data were collected at the energy industry center in Serbia, in the vicinity of coal mining areas and power stations, where the observed benzo(a)pyrene maximum concentration for a study period reached 43.7 ngm−3. The metaheuristics algorithm has been used to optimize the XGBoost hyperparameters, and the results have been compared to the results of XGBoost models tuned by eight other cutting-edge metaheuristics algorithms. The best-produced model was later on interpreted by applying Shapley Additive exPlanations (SHAP). As indicated by mean absolute SHAP values, the temperature at the surface, arsenic, PM10, and total nitrogen oxide (NOx) concentrations appear to be the major factors affecting benzo(a)pyrene concentrations and its environmental fate.

show abstract

“…Our previous studies have tackled issues in analysing air pollution in complex urban environments, including the need for proper contextualization of data [5], [6], [7], [8], [9], and the use of statistical methods and artificial intelligence algorithms [10], [11] and [12]. In terms of data modelling, metaheuristic algorithms are commonly used to address nondeterministic polynomial (NP)-hard problems, particularly in machine learning hyperparameter optimization, due to their stochastic nature.…”

Section: Computer Science and Artificial Intelligence Sessionmentioning

confidence: 99%

Revealing Toluene Behaviour in the Atmosphere Based on Coupling of Metaheuristics, Xgboost, and Shap

Jovanović¹,

Perišić²,

Stanišić³

et al. 2023

Proceedings of the International Scientific Conference - Sinteza 2023

View full text Add to dashboard Cite

This study used an improved version of the reptilian search algorithm to investigate atmospheric patterns of toluene and its interactions with other polluting species under different environmental conditions. Toluene is a harmful aromatic hydrocarbon known for its role in the formation of secondary atmospheric pollutants. In this study, a two-year database of hourly pollutant concentrations, such as toluene, was analysed. The results were validated against other models using metaheuristic algorithms, and Shapley's additive explanations method was used to interpret them. The findings indicated a distinct correlation between toluene and m,p-xylene, and the study described the environmental conditions that influence their interactions. Overall, this research highlights the significance of using advanced analytical techniques to better understand the relationships between pollutants and their behaviour in different environmental conditions.

show abstract

What Information on Volatile Organic Compounds Can Be Obtained from the Data of a Single Measurement Site Through the Use of Artificial Intelligence?

Cited by 4 publications

References 40 publications

Improving Tuberculosis Diagnosis using Explainable Artificial Intelligence in Medical Imaging

Improving Tuberculosis Diagnosis using Explainable Artificial Intelligence in Medical Imaging

Potential of Coupling Metaheuristics-Optimized-XGBoost and SHAP in Revealing PAHs Environmental Fate

Revealing Toluene Behaviour in the Atmosphere Based on Coupling of Metaheuristics, Xgboost, and Shap

Contact Info

Product

Resources

About