Journal of Problems in Computer Science and Information Technologies

DEVELOPMENT OF AN INTELLIGENT PASSENGER COUNTING SYSTEM FOR ENHANCING PUBLIC TRANSPORT EFFICIENCY AND OPTIMIZING ROUTE NETWORKS

2024-03-09T19:37:46+00:00

This study introduces a project aimed at the design and deployment of an intelligent passenger counting system for public transport. The objective is to enhance fare evasion control and reduce financial losses for transport operators through automated tracking of passenger entries and exits. The system employs the YOLO and DeepSORT algorithms, known for their high accuracy in identifying and monitoring passengers within complex environments. Experimental investigations reveal the critical role of camera type and positioning on system efficacy; notably, utilizing USB cameras over IP cameras enhances frame processing speed and overall system performance. However, testing has identified areas for improvement, particularly in managing group movements, minimizing frame loss, and increasing real-time accuracy. Future development efforts will focus on integrating depth sensors and crafting sophisticated data analysis algorithms to refine passenger counting precision during peak traffic periods. Anticipated outcomes of this project include optimized transport routes and schedules, improved management of passenger flows, heightened passenger satisfaction, and effective fare evasion prevention.

FLOOD FORECASTING IN MALAYA ALMATINKA RIVER VIA MACHINE LEARNING AND DEEP LEARNING WITH OVERSAMPLING

2024-03-24T19:57:14+00:00

Flooding, a phenomenon characterized by the overflow of water from its natural confines onto dry land, poses significant threats to communities and infrastructure, often resulting from heavy precipitation, snow melting, and various natural and anthropogenic factors. The causes of flooding encompass a myriad of influences, including intense rainfall, precipitation patterns, and meltwater accumulation. Such events precipitate abrupt rises in river and lake levels, accompanied by the formation of barriers. The breaching of dams and levees can trigger the rapid propagation of large volumes of water, generating formidable breach waves.

In contemporary flood management practices, machine learning and deep learning algorithms have emerged as indispensable tools for forecasting and mitigating flood risks. This study focuses on predicting floods in the Malaya Almatinka River, situated in Almaty, Kazakhstan. Leveraging a diverse set of algorithms including XGBoost, LightGBM, RandomForest, SVM, Linear Regression, and neural networks, the research endeavors to enhance flood prediction accuracy. However, during the data preprocessing phase, it was observed that the dataset suffered from imbalance, necessitating the implementation of Random Over-Sampling to rectify the issue and ensure more equitable representation across classes. Through the fusion of advanced computational techniques and empirical data, this research aims to contribute towards more effective flood forecasting strategies, thereby bolstering the resilience of communities in flood-prone regions.

USING NEURAL NETWORKS FOR DEMOGRAPHIC PREDICTION

2024-03-17T23:34:47+00:00

Currently, the big problem or opportunity is the collection and correct processing of data. Using a large amount of reliable data, as well as several types of data processing methods, it is possible to optimize many processes and the allocation of funds. Now, many neural networks are used throughout the Internet, an example of this is the use of neural networks to predict sales in retail. This method saves resources for analysts, speeds up work and provides round-the-clock monitoring, so it is possible to perfect sales in the market. This article also discusses the way of using a neural network to predict population demographic growth using neural networks. The proposed system should help perfect the distribution of funds and reduce the cost of demographic analysis. The article also discusses several methods of training a neural network to achieve this result. As a result of this research, it was possible to create a neural network model with a prediction accuracy of 99.7 percent.

CLASSIFICATION OF DANGEROUS ARRHYTHMIAS USING ECG SCALOGRAMS WITH DEEP CONVOLUTIONAL NEURAL NETWORKS

2024-03-17T23:23:39+00:00

In modern medicine, the problem of detecting and classifying life-threatening arrhythmias based on ECG data remains relevant and critically important for continuous patient monitoring. This study is dedicated to developing a method for the automatic classification of six classes of dangerous arrhythmias using short ECG segments of 2 seconds duration. Existing methods for detecting dangerous arrhythmias require additional improvements to ensure high accuracy and efficiency. The goal of this research is to develop an effective method for the classification of dangerous arrhythmias to facilitate timely medical intervention. A unique method is proposed, based on transforming ECG signals into scalograms using continuous wavelet transformation. For arrhythmia classification, the AlexNet neural network is employed. The study utilizes data from the PhysioNet database and synthesized ECG data using the SMOTE method. Experimental investigations demonstrated a high accuracy of the proposed method, with an average accuracy of 98.7% for all arrhythmia classes, surpassing previously achieved maximum estimates by other researchers (93.18%). The study has been successfully completed, showcasing scientific novelty and practical significance of the results. The proposed method not only improved existing accuracy estimates but also emphasized the potential of using scalograms and neural networks for recognizing dangerous arrhythmias from ECG data. This opens new horizons for continuous monitoring and timely medical intervention, enhancing the quality of patient care.

STUDY OF THE EFFICIENCY OF MATHEMATICAL MODELING FOR THE HEAT TRANSFER PROCESS

2024-03-17T15:03:23+00:00

This paper discusses mathematical methods and computational algorithms for the stationary process of heat transfer in artificial structures. We examined the temperature distribution inside the pipe depending on the radius, angle and length, which allowed us to conduct an in-depth analysis of the influence of various parameters on heat flows in the system. These results provide information to engineers and researchers working in the field of petroleum transportation, allowing them to better understand and optimize the thermal processes associated with this process. Modeling the thermal conductivity of pipelines is an integral part of the analysis of transportation processes, and the results of this study can be an important contribution to the design and control of technological processes in the energy and oil and gas industries. Due to the relevance of this topic, our work was carried out using the example of a literature review and control of the stationary oil heat transfer process. But the question of the relevance of the most effective and optimal methods for monitoring and controlling all heat transfer processes in various structures remains relevant.

UNLOCKING AGRICULTURAL AUTOMATION: INTEGRATING SLAM AND COMPUTER VISION FOR LIVESTOCK MANAGEMENT

2024-03-19T21:57:40+00:00

The use of autonomous livestock detection is crucial in modern agriculture, providing efficient control and management of animals. This article explores the use of the SLAM (Simultaneous Localization and Mapping) algorithm in conjunction with computer vision to address various challenges in enhancing the capabilities of autonomous robots and detecting livestock. Integrating computer vision and SLAM technology allows autonomous robots to successfully navigate complex conditions, adapt to dynamic environments, and accurately determine the location of livestock in real-time. This research also presents a method for simultaneously estimating the agent's position in space and mapping the surrounding environment. This approach enables robots to adapt to different lighting and weather conditions, ensuring reliable operation in various agricultural environments. Computer vision enables autonomous robots to accurately detect livestock based on visual data, enabling them to effectively monitor and manage animals. We discuss various issues that can be addressed using this combination of technologies, including navigation in unknown or changing environments, creating three-dimensional models of the surrounding environment, as well as autonomous control of robots and unmanned vehicles. This article also provides an overview of existing approaches and techniques used to address these issues, evaluating their advantages and limitations. In conclusion, we discuss the prospects for the development of this field and potential directions for future research.