Stream Analysis Research Articles

CelInsight:AI-Powered Web Solution for Cervical Cancer Classification

This paper introduces the system, a Python-based web platform developed for the secure management, processing, and intelligent analysis of medical images and video streams. The system leverages the great libraries and frameworks of Python, especially Flask, in building the backend.Through the emphasis on AI model integration of TensorFlow/PyTorch for better detection accuracy and precision.For the healthcare pro- fessionals.The report provides information about the architecture of the platform, the key features of the system, and how integrating AI transforms diagnostic workflows. Results indicate the system as a scalable, user-friendly, and secure tool for the management of medical images in health settings. It addresses the problem of cervical cancer as a health burden, with increased importance for low- and middle-income countries. Early and precise classification of cervical.Proper classification of cancer subtypes is crucial to guide the treatment decisions and to improve patient outcomes in those regions. In an attempt to solve this problem, the system develops a centralized imaging framework-based model intended for cervical cancer diagnosis classification. This framework is developed based on state-of-the- art imaging modalities and artificial intelligence. It improves the diagnostic workflow with greater efficiency and accuracy. The system presents hybrid models that are based on a combination of ideas of convolutional neural networks and Gradient-boosted machine learning classifiers are utilized for robust and reliable performance in the classification of various subtypes of cervical cancer. The system also ensures security and centralization of data; hence, the healthcare professionals get to work on scalable and accurate tools for the classification process. All these have been developed through Python-based technologies and incorporated into AI and secure infrastructure to make the system a pivotal innovation in modern diagnostics. Index Terms—Medical image processing, AI in healthcare, cervical cancer diagnosis, deep learning, convolutional neural net- works (CNN), Gradient-boosted machine learning, TensorFlow, PyTorch, Flask, diagnostic workflow, secure medical imaging, intelligent analysis, centralized imaging framework, healthcare technology, AI-driven classification, medical video stream analy- sis.

Utilizing Raspberry Pi and Internet of Things (IoT) Frameworks for Comprehensive Monitoring of Urban Pollutants and Climate Variables

Global warming is the effect of a rise in Earth's climate temperature due to air pollution. Urban areas have higher levels of air pollution than rural areas due to increased traffic and rapid development. In addition to brief health problems like headaches, eye infections, and throat in-factions, pollution also has lengthy health repercussions like lung cancer and heart disease. As a result, it's important to keep an eye on the many climatic and pollution indicators, including light intensity, temperature, humidity, air pressure, oxygen and carbon dioxide level and camera. Using suitable equipment and Internet of Things (IoT) technologies, a pollution and climate monitoring system is constructed in the proposed paper that can measure the parameters above at regular intervals. The system then uploads the data to a webpage in the Thing Speak. The IoT analytics platform service Thing Speak enables the collection, visualization, and analysis of real-time data streams. The sensors are used to feed data to Thing Speak, which instantly visualizes the data in a graph. The main tool for gathering data from the sensors and sending parameters to the website is the Raspberry Pi3 computer. The software code is developed using Python. By logging on to the website from any location in the world, one can view the submitted pollution and climate parameters of a specific location.

ПОВЫШЕНИЕ ПРОПУСКНОЙ СПОСОБНОСТИ РЕГУЛИРУЕМЫХ ПЕРЕКРЕСТКОВ НА ОСНОВЕ СИНЕРГИИ КОМПЬЮТЕРНОГО ЗРЕНИЯ И АДАПТИВНОГО РЕГУЛИРОВАНИЯ СКОРОСТИ

The paper discusses new approaches to the arrangement of non-stop traffic flows at signaled crossings using coordinated traffic management. The study objective is to develop a mathematical model for determining the recommended traffic speed on the stretches of the urban road network using computer vision to ensure the non-stop traffic of a group of vehicles when crossing a signaled intersection. The model is unique because it takes into account the queue parameters of out-of-group vehicles, as well as the condition of the road surface. The study presents a method for calculating the time of non-stop passage of cars over crossings of the road network using AIMS-Eco monitoring system. The system uses real-time video stream analysis technology based on YOLOv4 neural network to obtain data on traffic parameters. The coefficients of influence of the traffic flow structure and the condition of the road surface on the time of queuing outside the group vehicles are characterized, which makes it possible to more accurately assess the impact of these factors on traffic dynamics. The dependences studied include those of the recommended speed of the leading car and the capacity of the road network section on the number of extra-group vehicles, taking into account the travel time of the queue of extra-group vehicles. The developed mathematical model makes it possible to increase the average flow velocity in the section of the stop line by 10-15% due to the arrangement of non-stop passage of signaled intersections by group vehicles. The results achieved are of practical importance for increasing the traffic capacity of the road network, improving road and environmental safety of automobile traffic.

Analysis of Agricultural Marketing Data Flow and Optimisation Methods in Cross-Border E-Commerce Platforms

Big data technology makes it possible to scientifically analyse a large amount of marketing data, which plays an important role in the development of marketing strategies for products and the improvement of marketing effects. In this paper, a marketing data stream analysis system is designed based on the stream analysis method. The system designs and optimises the marketing data storage and retrieval, data acquisition and streaming calculation engine to achieve real-time user behaviour data streaming analysis. The average response time accuracy of the system’s data can reach 96%, the throughput rate is 11.8% ahead of the maximum compared to the Word Count system, and the before-and-after ratios of the PUSH message click rate, the user registration success rate, the online shop attention rate, the returning customer rate, and the loyal customer rate are 1.03, 1.02, 1.27, 1.11, 1.27, and 1.78, respectively. It indicates that this paper’s design of the marketing data streaming analysis system has good performance and application effect.

Identifying and Reducing Waste in the Chicken Carcass Production Process at PT. Ciomas Adisatwa

PT. Ciomas Adisatwa unit Berbah is one of the Poultry Slaughterhouses (PSh) in Yogyakarta, producing 2,000 chickens/hour. However, some production steps do not increase the value of the finished product. Because of that, wasteful and non-value-added production processes must be eliminated to reduce the risk of contamination in PSh products and make the production process more efficient. Therefore, this study aims to identify the causes of waste and find an appropriate system to reduce the waste process. The methods used in this study include the Value Stream Analysis Tools (VALSAT) technique and future state mapping. Lean manufacturing is a concept used to reduce or eliminate waste in a production process. The wastes identified in the PT Ciomas Adisatwa production process include waiting activity, inappropriate processing, and unnecessary motion. The material weighing process identified the waiting activity because it was waiting for the Delivery Order (DO). Inappropriate processing occurs in hair removal rework in a clean area. The third waste is unnecessary motion, movement that is not needed occurs in cutting operators and dirty processes. The proposed improvements to address these wastes include enhancing the integration of information flow systems using a computer network, adding a plucker machine, and clarifying the division of tasks for each workstation to avoid unnecessary motion.

A multi-cycle recursive clustering algorithm for the analysis of social media data streams

Events are usually embedded in latent topics and the extraction of these latent topics are enabled by event detection algorithms. Unsupervised algorithms like Clustering algorithms are very useful for detecting events but with requirements which may not be relevant or easy to determine when using unstructured textual social media data. For instance, some algorithms are required to be used on specific data shapes, but determining the shape of an unstructured data may not be practical aside from the high level of noise in the data. Many of the existing algorithms work well with structured data, however, some of these algorithms can be adapted to unstructured data with the caveat that cluster formations may not contain consistent contextual information. We propose a novel Multi-Cycle Recursive Clustering Algorithm (MCRCA), able to sequentially eliminate noise, resulting in high homogeneous cluster formations. MCRCA does not require the initial specification of clusters numbers as the estimated number of clusters can be deduced at convergence. Our algorithm out-performs the classical LDA and K-Means algorithms in forming highly homogeneous clusters, context-wise.

Analysis of Live E-commerce Influence on Consumers Shopping Behavior in the "Double 11" Shopping Festival in China

As one of the components of GDP calculation, consumption has always been the target of people's attention. Following the United States, China, the world's second-largest e-commerce market, is also a natural target. In particular, the research on the development of e-commerce and the rise of new shopping methods such as live e-commerce in recent years has aroused wide interest, and the analysis also provides new thinking for the sustainable development of e-commerce. In order to better study this problem, this study focuses on the analysis of online shopping and live streaming of goods in two ways. This study specifically analyzes the mechanism and rise of online shopping festivals and live streaming of goods, and also analyzes the possible advantages of the two methods and the shortcomings of product uncertainty as an example. In addition, this paper also combines and compares the two, especially in the "Double 11" shopping festival, and puts forward some thoughts for this research problem.

Modelling Concept Drift in Dynamic Data Streams for Recommender Systems

Recommendation systems play a crucial role in modern e-commerce and streaming services. However, the limited availability of public datasets hampers the rapid development of more efficient and accurate recommendation algorithms within the research community. This work introduces a stream-based data generator designed to generate user preferences for a set of items while accommodating progressive changes in user preferences. The underlying principle involves using user/item embeddings to derive preferences by exploring the proximity of these embeddings. Whether randomly generated or learned from a real finite data stream, these embeddings serve as the basis for generating new preferences. We investigate how this fundamental model can adapt to shifts in user behavior over time; in our framework, changes correspond to alterations in the structure of the tripartite graph, reflecting modifications in the underlying embeddings. Through an analysis of real-life data streams, we demonstrate that the proposed model is effective in capturing actual preferences and the changes that they can exhibit over time. Thus, we characterize these changes and develop a generalized method capable of simulating realistic data, thereby generating streams with similar yet controllable drift dynamics.

Electrodeposited Pt-Rh Thin Films for Enhanced Ammonia Oxidation Rates Via Electronic Modifications

Ammonia has garnered significant attention as a promising hydrogen carrier due to its high volumetric energy density, and its compatibility with existing fuel cell technologies. Electrochemical ammonia oxidation reaction (AOR) can facilitate the release of hydrogen from ammonia at the point of use, enabling on-demand hydrogen production without the need for high pressure storage. However, current AOR catalysts struggle with high overpotentials, sluggish kinetics and susceptibility to poisoning by AOR by-products. We report the AOR activity of electrodeposited bimetallic PtRh alloy nanoparticle catalysts. The dilute Pt92Rh8 catalyst showed less overpotential and higher activity than Pt and more concentrated PtRh samples. Valence-band X-ray photoelectron spectroscopy (XPS) showed that Rh shifts the d-band center of Pt towards the Fermi-level which tunes the adsorption energy of AOR intermediates. Furthermore, pre- and post-AOR nitrogen and oxygen XPS of the samples provided insight into the nature of poisoning species on the Pt and alloyed surfaces. The Pt-only surface was found to be more oxidized than the Pt92Rh8 surface post-AOR which indicates higher N2 selectivity and less NOx formation on the Pt92Rh8 surface. Analysis of product gas stream through gas chromatography will be reported. This study offers a design platform for the development of future Pt-based AOR electro-catalysts.

Implementation of Lean Manufacturing Approach Using Value Stream Mapping to Optimize Cycle Time and Reduce Process Waste (Case Study: CV. Teguh Jaya Mandiri)

Competition in several service sector companies and the manufacturing industry is getting tighter, which requires service companies as well as manufacturing to increase their production. Solving this problem can be started by improving the company system. Especially in minimizing or eliminating waste from the production process. CV. Teguh Jaya Mandiri is a company engaged in packaging screen printing services, its current condition has obstacles in the processing period that exceeds the time limit and does not match consumer demand. This is because the company has not done a good analysis in calculating the cycle time that occurs during the entire process. Thus, researchers can identify the level of waste and proposed improvements to optimize cycle time and reduce waste in the production process. In this research, the lean manufacturing method is used with the Value Stream Mapping tool followed by Process Activity Mapping which is one of VALSAT (Value Stream Analysis Tools). The results showed that Process Activity Mapping using the Value Stream Mapping approach identified waste in the production process at CV. Teguh Jaya Mandiri, namely there are overprocesses. The weighting result of overprocesses is 0,21. Cycle Time has decreased from 24812,5 seconds to 13908,5 seconds or 3 hours 52 minutes by eliminating NVA and reducing existing VA.

Imaging‐Based Lensless Polarization‐Sensitive Fluid Stream Analyzer for Automated, Label‐Free, and Cost‐Effective Microplastic Classification

The presence of microplastics in the environment is of significant concern, yet the exact extent of this pollution remains largely unknown. The ocean is of particular interest as the monitoring of microplastics presents a challenge in that in situ fluid stream solutions are not readily available and traditional sampling methods are labor‐intensive and costly. This study introduces an imaging‐based lensless polarization‐sensitive fluid stream analyzer (FSA) for automated, label‐free, and cost‐effective detection and classification of microplastics. The FSA incorporates digital in‐line holography and birefringence computation, enabling quantitative polarization‐sensitive imaging and machine‐learning‐based activities including sample classification. Birefringent textures of synthetic polymers are investigated owing to their optical anisotropy. A microplastic classifier is developed for the FSA and integrated to form an end‐to‐end workflow capable of sampling fluid streams and determining marine and microplastic particle presence. Cultures of two phytoplankton species form a simplified marine environment for FSA evaluation. The device is tested in a two‐class configuration for marine microorganisms and microplastics, as well as a five‐class configuration for marine microorganisms and four individual microplastic types (polyethylene, polyethylene terephthalate, polypropylene, and polystyrene). The results demonstrate high classification accuracy, supported by experiments in the simulated marine environment that validate the proposed implementation's efficacy.

Identifikasi Pemborosan dalam Proses Produksi Pakan Ternak Ayam di PT.XYZ dengan Menggunakan Metode Value Stream Analysis Tools (VALSAT)

This research aims to identify various types of waste in the chicken feed production process at PT. XYZ and provide improvement recommendations to reduce production costs. The method used is the Value Stream Analysis Tools (VALSAT) to map and analyze the value stream in the production process. This research includes direct observation and data analysis to find the main wastes. The results show seven main types of waste in the chicken feed production process: waiting time, unnecessary movements, product defects, excess inventory, inefficient processes, overproduction, and transportation. However, the research encountered several challenges, such as data limitations and difficulties in collecting accurate data. The largest waste found was excess inventory, with an average score of 9.13. This research provides clear insights into areas in the production process that require improvement. The implementation of the improvement recommendations is expected to increase the company's efficiency and productivity. Despite facing some challenges, the use of VALSAT proved effective in identifying and analyzing waste. It is hoped that the provided improvement recommendations can reduce waste and enhance operational efficiency at PT. XYZ.

INTELLIGENT VIDEO ANALYSIS TECHNOLOGY FOR AUTOMATIC FIRE CONTROL TARGET RECOGNITION BASED ON MACHINE LEARNING

Context. Target recognition is a priority in military affairs. This task is complicated by the fact that it is necessary to recognize moving objects, different terrain and landscape create obstacles for recognition. Combat actions can take place at different times of the day, accordingly, it is necessary to take into account the perspective of lighting and general lighting. It is necessary to detect the object in the video by segmenting the video frames, recognize and classify. Objective of the study is to develop a technology for the analysis of the development of a technology for recognizing targets in real time as a component of the fire control system, due to the use of artificial intelligence, YOLO and machine learning. Method. The article develops a video stream analysis technology for automatic target recognition of the fire control system based on machine learning. The paper proposes the development of a target recognition module as a component of the fire control system within the framework of the proposed information technology using artificial intelligence. The YOLOv8 pattern recognition model family was used to develop the target recognition module. The methods used during the study of the formed dataset. – Bounding Box: Noise – Up to 15% of pixels (limiting frame: adding salt and pepper noise to the image – up to 15% of pixels). – Bounding Box: Blur – Up to 2.5px (bounding box: adding Gaussian blur to the image – up to 2.5 pixels). – Cutout – 3 boxes with 10% size each (cut out a part of the image – 3 boxes of 10% size each). – Brightness Between –25% and +25% (changing the brightness of the image to increase the resistance of the model to changes in lighting and camera settings – from –25% to +25%). – Rotation – Between –15 and +15 (rotation of the image object – clockwise or counterclockwise by degrees from –15 to +15). – Flip – Horizontal (flip the image object horizontally). Results. The data is collected from open sources, in particular, from videos posted in open sources on the YouTube platform. The main task of data preprocessing is the classification of three classes of objects on video or in real time – APC, BMP and TANK. The dataset is formed using the Roboflow platform based on the labeling tools and subsequently the augmentation tools. The dataset consists of 1193 unique images – approximately equally for each class. The training was conducted using Google Colab resources. It took 100 epochs to train the model. Conclusions. Analysis is performed according to mAP50 (average precision as 0.85), mAP50-95 (0.6), precision (0.89) and recall (0.75). Big losses are due to the fact that the background was not taken into account during the research – training the module on the basis of confirmed data (images) of the background without technology

Ивент-анализ: применение в социальном прогнозировании

Monitoring the interrelationships between social events and phenomena and forecasting the dynamics of their changes are necessary in the conditions of instability of the modern world. There are many separate methods of analysis for social forecasting, however, for this research, the method of event analysis has been chosen, which is insufficiently considered in the scientific literature within the framework of this task, but has high potential. The purpose of the article is to adapt the event analysis methodology for its use as a social forecasting tool. The main data for the study was collected from the Russian information and news resource in the period 2020-2023. Based on the classical methodology of event analysis, the classifiers presented in this paper in the form of social spheres are defined in the research. As part of the analytical comparison stage, a graph analysis was carried out (graphs of relationships between categories were constructed, central nodes-categories were identified); time series analysis was performed (segmentation of time series by the PELT algorithm, clustering of time series by the k-means algorithm); key terms for press events were defined. The final product is an analytical dashboard with filters, statistics and interactive graphs. The analytical dashboard makes it possible to compare data in a static and dynamic state, to draw conclusions about the past and future states of objects of social forecasting. The main result of the research is the event analysis methodology developed by the author, which can be used for a comprehensive analysis of news streams, adapted to the necessary categories representing a certain entity or sphere, and applied in various social organizations or monitoring services.

Brownian motion in a magneto Thermo-diffusion fluid flow over a semi-circular stretching surface

The current study explores the mass and heat transport analysis of a Casson liquid stream past a curved surface. The current model considers the effect of magnetic strength brought on by the strength of the applied uniform magnetic field. The significance of thermophoresis and Brownian motion are also taken into account using the Buongiorno nano-liquid model. The study of liquid flow over stretching sheets frequently addresses practical issues that have garnered significant attention from researchers due to their importance in various domains, including microfluidics, fibreglass production, manufacturing, transportation, metal extrusion, thermal insulation, glass production, paper manufacturing, and acoustic blasting. The governing partial differential equations (PDEs) are converted into ordinary differential equations (ODEs) using the similarity variables. These equations are numerically solved using the finite difference method (FDM). The concentration, temperature, and velocity graphs were produced by varying the different physical parameters. The upsurge in the magnetic parameter reduces the velocity profile. As the magnetic parameter increases, thermal and concentration profiles upsurge. The decrease in velocity profile can be seen as the Casson parameter rises. The intensification in values of thermophoretic parameter enhances the thermal and concentration profiles. The concentration and thermal profiles reduce as the curvature parameter upsurges.

Acoustic streaming

In recent years, the need for accurate analysis of acoustic streaming has become urgent, as classical methods fail to quantify flows generated by acoustic waves beyond a few hundred kHz. This problem, identified since Lighthill’s seminal 1978 namesake publication, remains unresolved. Researchers, including myself, have relied on computational analysis and approximations to address some of these challenges. Few have examined the dynamic behavior of acoustic streaming—such as delayed onset, response to inharmonic excitation, and flows sustained after the acoustic wave stops—despite their importance in experiments. The difficulty lies in analyzing these flows. However, after extensive work on an alternative approach, we now have a method for closed-form analysis of one-dimensional acoustic streaming that includes transient behavior and accounts for nonlinear compressibility and viscous effects. We offer a coherent and straightforward plan for analyzing simple acoustic streaming cases where classical theories fail. This method can model both steady-state and transient acoustic streaming, potentially eliminating the need for computational analysis and providing enough physical insight for design purposes. Our goal is to equip listeners with the tools to perform this analysis themselves without need for tedious computational methods.

Transforming waste to wealth: Harnessing carbon dioxide for sustainable solutions

The escalating levels of carbon dioxide (CO₂) emissions present a critical challenge to global sustainability, considering that CO2 is the primary cause of climate change. This dilemma presents a unique opportunity: converting waste CO₂ into useful resources. This review provides an in-depth analysis of CO₂ sources and waste streams, examining their potential as feedstocks for various industrial processes. By reviewing cutting-edge conversion technologies—such as catalysis, electrochemical, and photochemical methods—this work emphasizes how revolutionary ideas in Carbon Capture and Utilization (CCU) can play a pivotal role in reducing greenhouse gas emissions while generating both environmental and economic advantages. Through a systematic review of case studies and success stories in Carbon Capture and Utilization (CCU), the review illustrates the practical viability of these technologies. Additionally, the challenges facing CCU implementation, including economic, technical, and policy-related barriers, are explored. The review fills a critical gap by providing a comprehensive overview of both the current state and future potential of CO₂ utilization. Finally, it outlines future directions, emphasizing the need for interdisciplinary approaches, policy frameworks, and technological advancements to fully realize the potential of harnessing CO₂ for sustainable solutions.

Sustainable practices in construction: Exposing the Potential of Waste as a Resource.

Abstract This paper examines the critical issues facing the construction and demolition industry in the countries of the European Union, with a particular focus on Germany. It presents strategies for waste management and sustainable development goals in construction sector. The construction industry is responsible for a significant proportion of waste production, which underscores the urgency of addressing the impending waste management crisis. The paper highlights the necessity for the implementation of circular-oriented construction practices that prioritize recycling and the reduction of waste, aiming to improve the efficient use of resources in building design and construction. Using a real non-residential building demolition as a case study, the paper outlines specific steps to determine building materials and document demolition procedures. This study presents a variety of selective demolition strategies, with consideration of end-of-life scenarios for materials, including reuse, recycling, and downcycling. The analysis highlights the complexity of the demolition process, emphasizing the necessity for comprehensive evaluation methodologies. By closing the material cycle and prioritizing reuse and recycling, it is possible to achieve sustainable and long-term value retention of building materials. Additionally, methods such as life cycle assessment and material flow analysis for waste streams are introduced. The environmental impact of the demolition of the “Elementum” office building in Munich was analyzed and the CO2 emissions calculated, in relation to transport distances. Results were presented on the reduction in CO2 emissions due to the elimination of transport to landfill and the associated impact on the Life Cycle Assessment. By considering factors such as resource conservation, energy consumption, greenhouse gas emissions, waste generation and pollution, stakeholders can make informed decisions to mitigate negative environmental impacts.

Applying Principal Component Analysis and Autoencoders for Dimensionality Reduction in Data Stream

This research focuses on the role and efficiency of Principal Component Analysis (PCA) and autoencoders, when working separately and concurrently for dimensionality reduction in large scale data. This is because the data obtained from sources such as the IoT sensors and the social media platforms is a lot more complicated than before and therefore proper dimensionality reduction is critical for real time analysis. The performance of these methods is analyzed on synthetic and real datasets based on which explained variance, reconstruction error and processing time of these methods are compared to define the optimal configuration. The results show that solely PCA is fast in linear data and autoencoders capture nonlinear dependence with slightly higher time complexity. This preserves considerable variance alongside a reasonable reconstruction error and thus makes the PCA-autoencoder model well suited to dynamic environments while incurring less computational expense than alternative PCA models. This work shows that it is possible to utilize relevant combinations of methods for dimensionality reduction to boost real-time data stream analysis especially in applications that demand for high accuracy at the same time as low delays.

Narratives Behind Climate Strategy in Finland

The 2015 Paris Agreement (PA) represents a profound change in global climate governance becoming a blueprint for other governance arenas. However, the varying success of reaching the national climate targets, unstable security, and growing right-wing populism poses a question of which direction the EU climate policy is moving after ten years of PA. The success of this agreement depends heavily on the effectiveness of national climate change policies wherein political parties have a critical role in developing these policies while also impacting public attitudes on climate change. We use the case of Finnish climate strategy as a case of national climate strategy. We analyzed Finnish climate policy documents by using Ostrom’s IAD Framework and Multiple stream framework analysis to create the narratives behind the Finnish climate strategy. The Institutional Analysis and Development framework (IAD) is a conceptual tool that Ostrom and her colleagues developed to analyze and understand the complex interactions and dynamics within institutions that govern common-pool resources. Our research question is: What are the narratives behind the Finnish climate strategy? Key words: Climate strategy, narrative, IAD framework, Multiple stream analysis framework