Browsing by Author "Demir, Muhammet"

Now showing 1 - 2 of 2

A Risk Assessment on Occupational Health and Safety in Fishing Activities in Gevas District (Van, Turkiye) for Healthcare Management
(Arman Darya inc, 2023) Cengiz, Ozgur; Demir, Muhammet; Sepil, Ahmet; Seremet, Mehmet
In this study, the commercial fishing activities, which is one of the oldest professions, is categorized as the most dangerous profession both in the world and in Turkey due to the workplace and working conditions. Diseases and accident rates are high in the aforementioned occupational group. The current study was carried out by face-to-face survey method with fishermen from April 2022 to September 2022 and the "L type matrix" method to evaluate possible risk factors in fishing activities in Gevas district in terms of occupational health and safety. The important risk factors; "Having no training in occupational health and safety (OHS)", and "Fatigue from irregular and long working hours" affect on the working conditions of the fishermen. This research is the first for Gevas region and is expected to be a reference for future studies.
Using Different Machine-Learning Algorithms to Predict Dissolved Oxygen Concentration in Rainbow Trout Farms
(Central Fisheries Research Inst, 2026) Karatas, Boran; Cakmakci, Cihan; Yucel, Elif Sena; Demir, Muhammet; Sen, Fazil
Dissolved oxygen (DO) is a vital parameter in intensive rainbow trout aquaculture, directly influencingfish growth, health, and survival. As such, accurate monitoring and prediction of DO levels are crucial for ensuring sustainable and efficient aquaculture practices. This study assessed and compared the predictive performance of four machine learning algorithms Multivariate Adaptive Regression Splines (MARS), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Averaged Neural Networks (avNNet) in estimating DO concentrations based on a range of water quality parameters. A total of 120 samples were collected from 12 rainbow trout farms across T & uuml;rkiye. The input variables included suspended solids, electrical conductivity, turbidity, nitrate, nitrite, ammonia, ammonium, orthophosphate, pH, water temperature, and total phosphorus. DO levels ranged between 8 and 15 mg/L. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percent Error (MAPE), and the coefficient of determination (R2). All models demonstrated strong predictive accuracy, with XGBoost achieving the best overall performance (MAE: 0.44, RMSE: 0.58, MAPE: 0.04, R2: 0.78), followed by RF, avNNet, and MARS. These findings highlight XGBoost as a robust predictor of dissolved oxygen levels in aquaculture systems, which may contribute to improving water quality management and increasing productivity in rainbow trout aquaculture.