Analele Universității ”Dunărea de Jos” din Galați. Fascicula II, Matematică, fizică, mecanică teoretică / Annals of the ”Dunarea de Jos” University of Galati. Fascicle II, Mathematics, Physics, Theoretical Mechanics

Cuprins

*** *** — 2025-07-28

Cuprins

Deep Learning for breast ultrasound analysis:

Iulia-Nela Anghelache Nastase — 2025-11-26

Breast ultrasound imaging is an essential tool in early breast cancer detection, yet its interpretation remains a challenging task due to image variability and noise. This study explores deep learning-based approaches for tumor segmentation and classification in breast ultrasound images, aiming to improve diagnostic accuracy and assist medical professionals in decision-making. An encoder-decoder architecture utilizing two pre-trained convolutional neural networks, DeepLabV3+ and U-Net, is proposed for the segmentation task. The segmentation performance was evaluated against a semi-automatic Local Graph Cut method using the Dice similarity coefficient. DeepLabV3+ achieved superior results compared to U-Net and Local Graph Cut.
Further, a deep learning framework incorporating MobileNetV2, VGG16, and EfficientNetB7 is employed for
classification. The proposed approach is novel in its ability to extract and analyze features from both the lesion and the surrounding tissue, leveraging morphological operations (erosion and dilation) to improve the model’s interpretability. Transfer learning allows for the optimization of classification performance. The system was trained and validated using the BUS-BRA and BUSI datasets. High accuracy and AUC scores were achieved for the classification of both benign and malignant lesions. These results confirm the effectiveness of CNNs in segmentation and classification tasks, highlighting the potential of deep learning for automated breast cancer diagnosis. The proposed methodology paves the way for more robust, interpretable, and clinically relevant AI driven diagnostic tools in breast imaging.

Signal analysis based on recurrence plots for effective driver behavior detection

Danut-Dragos Damian — 2025-11-26

This paper employs recurrence plots (RPs) generated from both accelerometer and gyroscope data to analyze driver behavior. It integrates visualization with quantitative analysis by extracting key recurrence quantification measures, such as the Recurrence Rate (RR), Determinism (DET), and Laminarity (LAM), to effectively characterize the dynamics of the time-series signals. The accelerometer and gyroscope data are collected along three axes. These recurrence-based features facilitate the discrimination between stable, controlled driving dynamics and irregular, non-deterministic driving behavior. The RPs are generated using a sliding time window.
The epoch length is set to 3000 samples with a window overlap of 80%. The results demonstrate that changes in driving conditions significantly altered the structure of the recurrence plots, with corresponding variations in the recurrence quantification RR, DET, and LAM metrics highlighting the sensitivity of these parameters to behavioral dynamics.

Using rational functions to improve the results of approximating a function

Ștefănuț Ciochină — 2025-11-26

In this article, we use rational functions in order to improve the results obtained in the approximation of a function in an interval [a, b]. For this we will approximate the function chosen as an example in this study using a ratio of two polynomials. To determine the two polynomials, we use the Taylor series expansion about the point x = 0 of the function chosen and the Padé approximation. Also, to highlight the accuracy of the obtained approximation, we analyze the absolute error between the initial function and the Pade approximation respectively and the Taylor series in the considered interval. The analyzed data, in the chosen interval, highlights much better results obtained by the Padé approximation compared to the Taylor series.

Assessment of heavy metal soil pollution adjacent to the streets of Galati city

Alina Sion — 2025-11-26

The objective of this study was to assess the level of soil pollution in the vicinity of streets from Galati city, with
different ages, traffic densities, and permitted speeds. Samples were collected from the surface (0–10 cm), at a
distance of 2–5 m from the edge of the streets, in duplicates. The immediate roadside area was avoided to eliminate the risk of accidental contamination. After determining the heavy metal concentrations, the degree of soil contamination was assessed using the following indices: the contamination factor (Cf), the pollution load index (PLI), the geoaccumulation index (Igeo), the enrichment factor (EF), and the metal pollution index (MPI).

Determination of pollutant elements in agricultural soil using X-Ray Fluorescence Spectrometry

Alina Sion — 2025-11-26

This study investigates the impact of agricultural practices on soil quality in Fundeni Commune, Galati County, with a particular focus on the potential contamination by heavy metals. Soil samples were collected from representative agricultural areas, including a vegetable garden, an alfalfa field, and two vineyards. The
concentrations of heavy metals were determined using X-ray fluorescence (XRF) spectroscopy, allowing both
qualitative and quantitative assessment. The analytical results indicated that, while the majority of measured
elements were within permissible limits, certain samples exhibited concentrations exceeding the normal
thresholds for arsenic (As), zinc (Zn), chromium (Cr), nickel (Ni), copper (Cu), and cadmium (Cd), suggesting
localized contamination potentially linked to agricultural inputs.

Assessment of lanthanum and cerium pollution in the Shatt al-Arab River

Raghad MOUHAMAD — 2025-11-26

The current study investigates the concentrations and bioaccumulation exponents (BAFs) of ten metal
compounds such as cerium (Ce), lanthanum (La), iron (Fe), calcium (Ca), magnesium (Mg), sodium (Na),
potassium (K), titanium (Ti), manganese (Mn), and phosphorus (P) from water and fish tissue samples of Iraq’s Shatt Al-Arab River. Samples were collected as May of the year 2018 from four sites distributed over a course of the river employing matching methods and gear. The metal grades were determined through X-ray Fluorescence (XRF) technology with proper calibration or standardization of a measuring device and method and quality control measures to provide reliable occurrences. The BAFs were derived as the proportion of the metal focus in fish tissues to its fixation in water. Descriptive factual studies were carried out to deconstruct the information and establish the normal, highest, lowest, and standard deviation qualities of every component. Information analysis unravelled massive differences in focuses of certain heavy metals between water and fish tissue tests from differing locations. The highest BAF values were noted for calcium, followed by titanium, magnesium and sodium, with very high bioconcentration of these metals in fish from the waterway. Overall, the results of this study present valuable information on natural presentation and health hazards posed by exposure to metals in fish and water samples from Shatt Al-Arab River