https://opendata.uni-halle.de//handle/1981185920/13588 Thu, 13 Aug 2026 06:36:37 GMT 2026-08-13T06:36:37Z https://opendata.uni-halle.de//handle/1981185920/126095 Title: Brain Tumor Mri Segmentation Using A Hybrid Otsu–Fcm Model Author(s): Enad, Fahad Hussein; Jaber, Asmaa Ghalib Abstract: The process of segmenting MRI images of brain tumors is one of the essential tasks in image-based medical diagnosis, as it directly contributes to improving the accuracy of determining the tumor's location, shape, and size. However, most segmentation techniques still suffer from poor performance in low-contrast or noisy images due to the overlap of gray levels and the similarity of brain tissues. This study aims to develop an effective hybrid model that combines Otsu’s Method and the Fuzzy C-Means (FCM) algorithm, in order to enhance segmentation accuracy and reduce the impact of noise in medical images. The model was implemented using the MATLAB environment and applied to the BraTS 2023 database, which includes MRI images of 1271 patients. The evaluation methodology included the extraction of multiple quantitative indicators such as the Dice coefficient, Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), accuracy, recall, and F1 score. The results showed that the hybrid model outperformed the individual methods; the average Dice coefficient was 0.9577, compared to 0.9262 and 0.8955 for the FCM and Otsu methods, respectively. The model also achieved the lowest mean squared error (MSE = 94.58) and the highest PSNR of 29.17 dB, with a classification accuracy of 98%. These results confirm that the proposed model provides an effective balance between computational accuracy and structural flexibility, making it suitable for application in medical decision support systems, especially in analyzing medium or low-quality images without the need for complex deep models. Mon, 01 Dec 2025 00:00:00 GMT https://opendata.uni-halle.de//handle/1981185920/126095 2025-12-01T00:00:00Z https://opendata.uni-halle.de//handle/1981185920/125897 Title: Temporal Dependency Analysis in Short-Term Electricity Load Forecasting Using Ensemble Learning Author(s): Zhumagali, Ilias; Ramatullayeva, Meruyert; Amanzhol, Symbat; Turkbenbayev, Turlan; Kachan, Dmitry Abstract: Accurate short-term electricity load forecasting is essential for reliable operation of modern power systems and smart grid infrastructures. This study investigates the temporal dependency structure of household electricity consumption using supervised machine learning techniques. The forecasting task is formulated as a regression problem based on lagged load values, calendar-related temporal features, and exogenous meteorological variables, including air temperature, relative humidity, precipitation, and wind speed. Linear Regression is employed as a benchmark model, while Random Forest is used as a nonlinear ensemble approach. Model performance is evaluated using Mean Absolute Error, Root Mean Square Error, and Mean Absolute Percentage Error under chronological train-test splitting in order to preserve temporal causality. In addition, lag-window sensitivity analysis, walk-forward validation, multi-step forecasting horizon analysis, and feature importance assessment are conducted. The Random Forest model with weather variables achieved the best one-hour-ahead forecasting performance, with MAE of 0.397, RMSE of 0.552, and MAPE of 54.27%. The results show that recent load history and daily periodicity remain the dominant predictors, while meteorological variables provide a limited but measurable contribution. The findings support the use of ensemble learning for short-term load forecasting analysis and highlight the need for further refinement when applying such models to highly volatile residential consumption patterns. Wed, 01 Apr 2026 00:00:00 GMT https://opendata.uni-halle.de//handle/1981185920/125897 2026-04-01T00:00:00Z https://opendata.uni-halle.de//handle/1981185920/125896 Title: Results of Experimental Study of Photovoltaic Installation Based on Thin-Film Panels for Integration on Facade of the Building Author(s): Juraeva, Zukhra; Yuldoshev, Isroil; Juraev, Islom Abstract: This article presents the results of experimental studies of a photovoltaic installation (PVI) based on thin-film cadmium telluride panels. The aim of the work was an experimental study of the PVI for integration on the facade of the building. For the research, PVI was prepared by assembling photovoltaic panels (PVP) into window blocks. This installation consists of two parts. The design of the first part PV1 allows to change the angle of inclination relative to the horizon. The second part of PV2 has a strictly vertical orientation. The research was conducted in the geographical conditions of Tashkent in July-August and September-November 2025. The experimental results showed a significant dependence of the performance of photovoltaic installations on the angle of inclination to the horizon, on the seasons and weather conditions. For vertically installed PVP, the use of reflective devices that concentrate the sun's rays proved effective in the summer. According to preliminary studies, the use of reflectors has increased the flow of solar radiation to the surface of photovoltaic panels by an average of 25%, and electricity generation by 14%. In the summer, the optimal PVP tilt angle for the geographical area under study was 33°. The second stage of the research was the study of PVI's work in the autumn period of the year. The measurement results for this period showed that the PVP power at vertical orientation was 16% higher than the PVP power at an angle of 33°, and 13% less than the PVP power at an angle of 60° to the horizon. The conducted experimental studies make it possible to determine the geometric and energy parameters of PVI for optimal integration on the facade of the building. Wed, 01 Apr 2026 00:00:00 GMT https://opendata.uni-halle.de//handle/1981185920/125896 2026-04-01T00:00:00Z https://opendata.uni-halle.de//handle/1981185920/125895 Title: Impact of Thermal Parameters on the Performance of Photovoltaic Panels in Pump Water Solar Systems: A PVsyst Simulation Study Author(s): Rabih, Samer; Zakzouk, Ammar; Hasan, Hasan; Abdullatif, Mazen; Nouman, Ziad; Malla, Ahmad; Mousa, Rami Abstract: Solar energy has emerged as one of the most efficient and sustainable renewable sources for powering water pumping systems, particularly in rural and agricultural regions where conventional electricity grids are unavailable. Photovoltaic (PV) water pumping systems (WPS) provide an independent and cost-effective alternative that supports both energy and water security. In this study, a solar-powered water pumping system was designed and simulated using PVsyst software to drive an 11-horsepower submersible pump. The analysis investigated the influence of various PV panel technologies and thermal parameters, focusing mainly on the open-circuit voltage temperature coefficient (μVoc), on system efficiency and annual water yield. Simulation results demonstrated that PV panel technology and thermal behavior have a measurable impact on overall system performance, with lower (less negative) μVoc values leading to higher pumping efficiency and water output. The findings confirm that selecting panels with improved thermal characteristics significantly enhances system productivity and economic viability. This research contributes to optimizing PV-based pumping design for sustainable agricultural applications, promoting renewable energy adoption, and supporting the achievement of long-term water and energy sustainability goals. Wed, 01 Apr 2026 00:00:00 GMT https://opendata.uni-halle.de//handle/1981185920/125895 2026-04-01T00:00:00Z