The article focuses on enhancing stock market price prediction through artificial neural networks and machine learning. It underscores the significance of improving forecast accuracy by incorporating historical stock prices, macroeconomic indicators, news events, and technical indicators. Exploring deep learning principles, it delves into convolutional neural networks (CNN), recurrent neural networks (RNN), including long short-term memory (LSTM), and gated recurrent unit (GRU) modifications. This financial time series processing study covers data preprocessing, creating training/test sets, and selecting evaluation metrics. Results suggest promising applications for the developed forecasting models in stock markets, stressing the importance of considering various factors for precise forecasts in dynamic financial environments. Historical reserve data serves as the model foundation. Integration of macroeconomic, news, and technical indicators offers a holistic approach, aiding trend and anomaly identification for enhanced forecasts. The article recommends suitable deep learning architectures, highlighting LSTM and GRU's effectiveness in adapting to intricate data dependencies. Experimental outcomes showcase these architectures' benefits in predicting stock market prices, offering valuable insights for finance and asset management professionals in financial analysis and machine learning realms.
31 August 2023 in Eastern-European Journal of Enterprise Technologies
In modern medicine, laboratory tests play an important role in the diagnosis, treatment and monitoring of patients. However, the volume and complexity of the data obtained can create challenges for interpreting the results. In this paper, we present a study on the application of integrated automation of a medical laboratory using OpenAI for a more accurate and effective interpretation of laboratory results. Interpreting laboratory results through integrated automation using artificial intelligence (AI) and other digital technologies automatically analyzes and interprets laboratory results. This approach aims to streamline the process of interpreting laboratory results and provide more accurate, consistent and timely results to healthcare providers. Comprehensive automation of the interpretation of laboratory results can improve the efficiency and accuracy of laboratory results, leading to improved patient outcomes and better clinical decision-making. However, it is essential to note that AI models are imperfect and can still make mistakes. Therefore, healthcare professionals should always review automated interpretation results before diagnosing or treating. The work presented results in applying OpenAI to interpret laboratory results in the laboratory information system smartLAB Kazakhstan, which provides a complete cycle of automation of all medical laboratory processes. In the course of the study, an automated information system of a medical research complex using artificial intelligence was developed and implemented
This paper explores the feasibility of early-season crop classification based on Sentinel-2-time series using the TimeSen2Crop dataset (≈1 million pixels, 16 crops). The aim of the study was to evaluate the spectral-phenological separability of crops during the season and compare the performance of classical tabular algorithms, deep sequence models, and a seasonally oriented hybrid stacking scheme. Based on multispectral observations, a feature set was formed from 9 optical channels and 13 vegetation indices for 30 dates. F-criteria were calculated, confirming a sharp increase in interclass separability during the active vegetative growth phase and substantiating three time series truncation scenarios (early, early + mid-season, and full season). Random Forest (macro-F1: 0.46/0.74/0.75) was used as the base tabular model. LSTM, BiLSTM, GRU, 1D-CNN, and Transformer were trained in parallel, with Transformer showing the best results among the deep architectures (0.42/0.68/0.78). The main contribution of the work is a hybrid multi-layer stacking scheme combining heterogeneous base algorithms and OOF meta-features, which provides the highest quality (0.51/0.83/0.86) in all scenarios. The obtained results confirm the effectiveness of phenology-oriented selection of time windows, informative indices, and hybrid ensemble learning for improving the accuracy of early-season crop monitoring.
This paper presents a reproducible system innovation for processing Digital Imaging and Communications in Medicine (DICOM) mammography images based on pixel-monotonic dynamic range management and engineering-verifiable intensity transformations. Standard DICOM conversion schemes to 8-bit representation often result in irreversible luminance-range compression, locality-dependent contrast distortions, and reduced robustness of deep learning models. The proposed framework preserves the physical consistency of the Modality LUT and photometric polarity, performs breast-aware robust Winsor normalization, and applies strictly monotonic global tone mapping while preserving the 16-bit depth of the training data. System validation was performed using architecture-independent metrics. Compared to standard processing, the median value of normalized mutual information increased from 0.878 to 0.892, the effective number of bits increased from 7.88 to 10.11 (+2.25), the representation entropy increased by 1.42 bits, and the clipping rate was reduced to almost zero. Experiments with the Faster R-CNN detector showed stable or improved calcification localization at Intersection over Union (IoU) ≥ 0.5 under controlled augmentation conditions. The results confirm that pixel-monotonic dynamic range control provides a reproducible, engineering-verifiable basis for AI-based mammography analysis within the evaluated dataset and experimental setting.
Rare event detection in large tabular data remains a computationally challenging problem due to class imbalance, heterogeneous feature distributions, and unstable thresholds. Traditional machine learning approaches based on individual models and fixed thresholds often exhibit limited robustness and reproducibility in such settings. This paper proposes a hybrid ensemble framework for rare event detection that integrates heterogeneous machine learning models through threshold-aware probabilistic aggregation. The framework combines gradient-boosted decision trees, regularized linear models, and neural networks, leveraging their complementary inductive biases. To ensure reproducibility and robust performance evaluation under severe class imbalance, a leaky-controlled evaluation protocol is employed, including rootwise summation, probability calibration, and validation-based threshold optimization. The proposed approach is evaluated on a large tabular dataset containing approximately 50,000 observations. Experimental results demonstrate improved rare event detection and robust generalization performance compared to individual baseline models. Explainability is achieved through Shapley Additive Explanations (SHAP)-based attribution analysis and clustering in the explanation space, enabling transparent analysis of ensemble decision-making behavior. The proposed framework represents a general-purpose computational solution for rare event detection and can be applied to a wide range of data-driven decision-making and anomaly detection problems.
20 June 2025 in International Journal of Innovative Research and Scientific Studies
The purpose of this study is to develop a robust methodology for the automated detection and quantitative analysis of tandem repeats in genomic sequences, taking into account mismatches and distances, to enhance primer design and improve the accuracy of genomic research. The approach combines an efficient algorithm for identifying complementary DNA fragments, focusing on the 3' end of primers, and integrates two independent similarity metrics: the Hardy–Weinberg χ² test and cosine similarity. The methodology involves generating similarity matrices, heat maps, 3D surface visualizations, and scatter plots for comprehensive evaluation of sequences. Experimental validation of the complete genome of Lactobacillus brevis ATCC 367 identified 586 tandem repeats, demonstrating high consistency between the two metrics and revealing high similarity among most repeats, while highlighting specific cases with discrepancies that require further investigation. The developed methodology effectively combines statistical and vector analyses, enhancing the reliability of genomic studies and enabling the identification of biologically significant variations. The proposed tool can be widely applied in molecular biology, especially for primer design, genome annotation, and biomarker discovery. It is scalable and adaptable to large genomic datasets, making it suitable for high-throughput bioinformatics analyses.