Reduce Processing Time Research Articles

ACORDO DE NÃO PERSECUÇÃO PENAL (ANPP): UM ESTUDO DO POSSÍVEL IMPACTO PARA A EFICIÊNCIA DO SISTEMA DE JUSTIÇA CRIMINAL BRASILEIRO

The Non-Prosecution Agreement (ANPP), introduced by Law No. 13.964/19, is a legislative innovation aimed at increasing the speed and efficiency of the Brazilian criminal justice system. This article analyzes the impact of the ANPP on the streamlining of processes and the reduction of processing time, based on empirical data from the "Justice in Numbers 2020 at 2024" reports by the CNMP and specific studies on the subject. The research highlights the importance of the ANPP in promoting justice in the criminal sphere, contributing to a more agile and effective penal system. The analysis covers the genesis of the ANPP, its normative contours, and practical application, as well as its possible impacts on the criminal justice context, with an emphasis on reducing procedural overload and improving system efficiency, especially regarding procedural speed. Finally, the limitations and challenges faced in the application of the ANPP will be discussed, as well as future prospects for its consolidation as an effective criminal justice mechanism.

Enhancing Localization Accuracy and Reducing Processing Time in Indoor Positioning Systems: A Comparative Analysis of AI Models

This paper presents a comparative study of different AI models for indoor positioning systems, emphasizing improvements in localization accuracy and processing time. This study examines Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNNs), and the Kalman filter using a real Received Signal Strength Indicator (RSSI) and 9-axis ICM-20948 sensor. An in-depth analysis is provided in this paper for data cleaning and feature selection to reduce errors for all the models. We evaluate these models in terms of localization accuracy and prediction time. The RNN model shows the best performance, achieving a localization error of 0.247 m with a delay of 0.077 s per position location for an area of 12m×9.5m using four anchors. This research highlights the importance of selecting AI models for effective mobile tracking according to test and validation data.

Analisis Produktivitas dan Efektivitas Pada Pembuatan Alat Pengupas Kulit Kelapa Muda

This study aims to design and analyze a young coconut skin peeling tool to improve efficiency and safety in the coconut-cutting process, which is currently done manually. The manual process, which takes an average of 3 minutes per coconut, is potentiallyinefficient and risky. With the development of this tool, it is expected to speed up the peeling process, increase productivity, and support the growth of Pak Agung's business in Sidoarjo Regency. The methods used in this study include productivity analysis and effectiveness analysis of the tool. The productivity analysis was conducted by calculating the time required to peel a certain number of coconuts before and after the use of the tool, while the effectiveness analysis evaluates how much the tool can reduce processing time and increase the number of coconuts that can be processed in a unit of time. The analysis results show that after using the tool,the time needed to peel 30 coconuts was reduced from 95 minutes to only 16 minutes, and the processing time per coconut dropped from 3 minutes to 32 seconds. This achievement shows a significant improvement, reflecting better operationalefficiency. This study emphasizes the importance of innovation in tools and technology to support the sustainability of micro and small businesses, as well as to contribute positively to the performance of the coconut processing industry. Keywords: Cost Analysis, Effectiveness, Productivity, Product Design

Enhanced Fault Prediction for Synchronous Condensers Using LLM-Optimized Wavelet Packet Transformation

This paper presents an enhanced fault prediction framework for synchronous condensers in UHVDC transmission systems, integrating Large Language Models (LLMs) with optimized Wavelet Packet Transform (WPT) for improved diagnostic accuracy. The framework innovatively employs LLMs to automatically optimize WPT parameters, addressing the limitations of traditional manual parameter selection methods. By incorporating a Multi-Head Attention Gated Recurrent Unit (MHA-GRU) network, the system achieves superior temporal feature learning and fault pattern recognition. Through intelligent parameter optimization and advanced feature extraction, the LLM component intelligently selects optimal wavelet decomposition levels and frequency bands, while the MHA-GRU network processes the extracted features for accurate fault classification. Experimental results on a high-capacity synchronous condenser demonstrate the framework’s effectiveness in detecting rotor, air-gap, and stator faults across diverse operational conditions. The system maintains efficient real-time processing capabilities while significantly reducing false alarm rates compared to conventional methods. This comprehensive approach to fault prediction and diagnosis represents a significant advancement in synchronous condenser fault prediction, offering improved accuracy, reduced processing time, and enhanced reliability for UHVDC transmission system maintenance.

Numerical Simulation and Experimental Analysis of Mare’s Milk Sublimation Drying

This study presents a combined numerical and experimental analysis of heat and mass transfer in mare’s milk during vacuum sublimation drying, which is a process essential for producing high-quality powdered products. The numerical model was developed using two-dimensional simulations and validated against experimental data obtained for varying sample thicknesses (3 mm, 5 mm, and 7 mm). Results demonstrated a strong agreement between the model and experimental temperature data, with a coefficient of determination (R2) of 95% during the sublimation process. The findings revealed that thinner samples (3 mm) exhibited a 20% faster drying rate than thicker samples (7 mm), highlighting the critical role of sample thickness in sublimation dynamics. Additionally, the effects of heat flux distribution and mass loss due to sublimation were analyzed to understand the drying dynamics. This study highlights the importance of optimizing process parameters such as chamber pressure, shelf temperature, and sample thickness to enhance drying efficiency and reduce processing time. The findings provide valuable insights for scaling vacuum sublimation drying of mare’s milk for industrial applications.

An Efficient Smart Flood Detection and Alert System based on Automatic Water Level Recorder Approach using IoT

An innovative flood detection system may track an increase in water levels. Deployed in cities or other areas of interest, the system consists of sensors. Both mains energy and solar power are viable options for the sensors. To detect impending flooding promptly, a flood warning system uses reliable and up-to-date sensing equipment such as rain gauges, water level sensors, and flow rate sensors for the smart alert system. The challenging characteristics of smart flood detection and alert systems are that some people may not be able to access the warnings, and flash floods may happen too quickly for a warning to be adequate. Hence, in the proposed method, the Automatic Water Level Recorder enabled the Internet of Things (AWLR-IoT), which integrates a low-cost cloud to overcome the challenges of the smart flood detection and alert system and increase optimization modelling and efficiency. Among the most destructive natural catastrophes that may happen on Earth is flooding. After that, a Wireless Sensor Network (WSN) is used to accomplish the flood prediction utilizing data from sensors enabled by the Internet of Things. Heavy rainfall and the following water outflow cause flooding in nations with certain climate conditions. The system monitors humidity, temperature, water level, water rise rate, and rainfall to identify when a flood is imminent. The function of the AWLR-IoT sensor is for monitoring and recording in a database with real-time sensing. This research shows that the low-cost AWLR-IoT sensor has reduced processing time compared to conventional data processing.

Beyond processing methods: the impact of the drying technique on PET performance

Plastic materials are essential in modern societies, and their recycling is a very important step in the transition towards a circular economy. PET (polyethylene terephthalate) is currently considered one of the plastics with the greatest potential for recycling due to its good properties and ability to be processed by industrial methods. However, those processes may deteriorate PET properties, since they involve high temperatures and shear stresses that together with the presence of moisture (due to the strong hydrophilic nature of PET) can provoke hydrolysis of the polymer with a corresponding loss in molecular weight. When working with recycled PET the excess moisture contained in the material may be higher. It is evident the huge importance of the drying stage in the processing of this resin. However, it has not been yet studied the influence of different techniques on the final mechanical properties of processed parts and on the processing cycle (time/costs). In this work, two drying techniques were applied: a convection oven—widely used in the industry—and an infrared oven. The aim was to study the influence of this part of the processing cycle on the final mechanical properties of PET parts obtained from both virgin material and waste soda bottles. Results confirmed that drying by infrared technology reduces drying time by 80% which implies a drastic reduction in total processing time for both types of PET (virgin and recycled). Even though no significant differences were found in the conventional and non-conventional mechanical properties, differences in the propagation mode under fracture were noticeable. These were found to be due to unintentional esterification reactions induced by IR radiation in thick materials, probably due to heat concentration, that should be taken into account when this drying technique is intended to be used.

The impact of ChatGPT integration and customer relationship management on MSME sales performance with operational efficiency as a mediating variable

In an increasingly advanced digital era, micro, small, and medium enterprises (MSMEs) face new challenges and opportunities in enhancing their sales performance. The use of innovative technologies, such as ChatGPT and Customer Relationship Management (CRM), is key to improving operational efficiency and strengthening MSME competitiveness. This study aims to analyze the impact of integrating ChatGPT and CRM on MSME sales performance with operational efficiency as a mediating variable. The research employs a quantitative approach using SEM-PLS methodology to explore the relationships between relevant variables. The study was conducted on 100 MSMEs in Subang Regency, Indonesia, using an online questionnaire as the data collection tool. The findings indicate that the integration of ChatGPT and CRM significantly affects MSME sales performance in Subang Regency, with operational efficiency as a mediating variable. First, ChatGPT has been shown to have a significant positive impact on MSME sales performance. This technology facilitates the adoption of new technologies, enhances customer interaction, and enables better service personalization, which directly impacts increased sales volume, sales growth, and revenue. Second, effective CRM implementation also demonstrates a significant positive influence on MSME sales performance. Good customer data management, customer satisfaction, and customer loyalty contribute to increased sales volume, sales growth, and revenue. Third, operational efficiency proves to play a significant mediating role in the relationship between ChatGPT and CRM integration and MSME sales performance. Improvements in operational efficiency through reduced processing times, optimized resource use, and cost reduction support increased sales volume, sales growth, and revenue.

The Impact Of Revolution 5.0 on Digital Government and Public Service Efficiency

This study explores the impact of Revolution 5.0 on public service efficiency in the context of digital governance. The primary aim of the research is to assess how advanced technologies such as Artificial Intelligence (AI), Big Data, and the Internet of Things (IoT) are influencing the performance and efficiency of government services. This study uses a quantitative research approach, employing a descriptive and explanatory design to describe the phenomenon and analyze the relationship between Revolution 5.0 technologies (independent variable) and public service efficiency (dependent variable). Data were collected through a survey administered to 250 respondents, including government employees, State Civil Apparatus (ASN), and the public, using a structured questionnaire with Likert scale items. The findings indicate that the integration of digital technologies significantly enhances administrative efficiency, reduces processing time, and improves public satisfaction with government services. The study contributes valuable insights into the ongoing digital transformation in public administration and provides recommendations for improving digital literacy among civil servants to further optimize service delivery.

Enhancing surface roughness of material extrusion additive manufacturing components via an innovative ironing process

ABSTRACT Extrusion-based 3D printing is widely used in various industries, enabling the rapid creation of prototypes and functional parts at a lower cost compared to traditional technologies. However, one limitation of this technology is the surface finish of the components, where the roughness is not optimal. This paper presents a solution to improve the surface finish of components by leveraging the principles of ironing and ball burnishing. The tool, appropriately heated and passed over the component, smooths out imperfections by uniforming the surface profile. Unlike the traditional ironing method, the use of this tool reduces processing times and enhances surface roughness with a simpler construction and control mechanism compared to a conventional hot-end. The average surface roughness obtained is Ra = 0.796 μm; these values are comparable to those obtained by grinding. The geometry of the tool tips can vary significantly based on specific applications.

Developments in Radiofrequency Processing Applications on Food of Animal Origin

Radio frequency (RF) treatment is one of the novel dielectric heating techniques for foods. It is an indirect process whereby electrical energy is initially transformed into electromagnetic radiation, which then generates heat within the food. Radiofrequency heating has been found some advantages like rapid heating or deep penetration into food compare to conventional methods. Traditional heat treatments applied to animal products can lead to quality losses, color and texture changes, overheating problems and other undesirable side effects. RF treatment has the potential to minimize these problems, improve organoleptic quality, reduce process time and save energy. Recently, the most investigated methods for animal origin foods are RF pasteurization/sterilization, RF-supported thawing methods, RF heating or cooking and the results obtained are promising. Radiofrequency technique is also investigated for following purposes; blanching, post-bake drying, roasting and disinfection. The new generation of RF studies explore other aspects, including the discovery of dielectric properties of foods, the evaluation of efficiency and quality effects, environmental sustainability of RF technologies and the improvement of RF system performance. Also combined systems are investigated such as radiofrequency-assisted cryogenic freezing. This paper reviewed principles of RF, overview situation of RF treatment methods and recent literature on RF applications on food of animal origin.

Advancing Applications of Robot Audition Systems: Efficient HARK Deployment with GPU and FPGA Implementations

This paper proposes efficient implementations of robot audition systems, specifically focusing on deployments using HARK, an open-source software (OSS) platform designed for robot audition. Although robot audition systems are versatile and suitable for various scenarios, efficiently deploying them can be challenging due to their high computational demands and extensive processing times. For scenarios involving intensive high-dimensional data processing with large-scale microphone arrays, our generalizable GPU-based implementation significantly reduced processing time, enabling real-time Sound Source Localization (SSL) and Sound Source Separation (SSS) using a 60-channel microphone array across two distinct GPU platforms. Specifically, our implementation achieved speedups of 23.3× for SSL and 3.0× for SSS on a high-performance server equipped with an NVIDIA A100 80 GB GPU. Additionally, on the Jetson AGX Orin 32 GB, which represents embedded environments, it achieved speedups of 14.8× for SSL and 1.6× for SSS. For edge computing scenarios, we developed an adaptable FPGA-based implementation of HARK using High-Level Synthesis (HLS) on M-KUBOS, a Multi-Access Edge Computing (MEC) FPGA Multiprocessor System on a Chip (MPSoC) device. Utilizing an eight-channel microphone array, this implementation achieved a 1.2× speedup for SSL and a 1.1× speedup for SSS, along with a 1.1× improvement in overall energy efficiency.

OPTIMIZATION METHODS FOR PARAMETER IDENTIFICATION MODEL OF TEST ELECTRORETINOSIGNAL TO ASSESS NEUROTOXICITY RISKS

Introduction. The development of advanced optimization methods plays a crucial role in the enhancement of diagnostic tools in the biomedical field, particularly in the analysis of complex physiological signals. Electroretinography (ERG) is a widely used diagnostic technique that records electrical responses generated by the retina in response to light stimuli, providing valuable insights into the functional health of retinal cells. ERG is instrumental in diagnosing conditions such as retinitis pigmentosa, diabetic retinopathy, and neurotoxicity. However, the analysis of low-intensity electroretinograms (ERG) presents numerous challenges, particularly due to noise and signal distortion, which complicate accurate signal interpretation. Main purpose of this study.This paper is dedicated to developing an expert system for real-time analysis of electroretinographic signals (ERS), focusing on optimizing the parameters of a mathematical model for ERS analysis in conditions where noise and other distortions are present. The primary aim is to improve the accuracy and efficiency of ERG data processing, enabling early detection of neurotoxicity and other retinal conditions. To achieve this, we applied advanced optimization techniques, such as the Nelder-Mead method, known for its effectiveness in handling non-smooth, noisy functions. Conclusions. 1. The application of the Nelder-Mead algorithm for optimizing the complex and noisy ERS model significantly improved the performance of ERG data analysis. The algorithm's adaptability to varying optimization conditions allowed for more accurate model parameter determination, particularly in the context of real-time neurotoxicity detection. Reduction in Processing Time: The time complexity analysis revealed that the Nelder-Mead method reduced the time required to compute the model coefficients by approximately 15%. This improvement was achieved while maintaining the necessary precision for reproducing the test electroretinosignal, making it suitable for real-time applications. Computational Efficiency: One of the key findings of this study is that the use of the Nelder-Mead algorithm reduced the computational load by up to 30%. This makes the method feasible for use in expert systems designed for real-time ERS analysis, allowing for the monitoring of functional changes in the retina during the early stages of neurotoxicity detection.

Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization

In geoenergy science and engineering, well placement optimization is the process of determining optimal well locations and configurations to maximize economic value while considering geological, engineering, economic, and environmental constraints. This complex multi-million-dollar problem involves optimizing multiple parameters using computationally intensive reservoir simulations, often employing advanced algorithms such as optimization algorithms and machine/deep learning techniques to find near-optimal solutions efficiently while accounting for uncertainties and risks. This study proposes a hybrid workflow for determining the locations of production wells during primary oil recovery using a multi-modal convolutional neural network (M-CNN) integrated with an evolutionary optimization algorithm. The particle swarm optimization algorithm provides the M-CNN with full-physics reservoir simulation results as learning data correlating an arbitrary well location and its cumulative oil production. The M-CNN learns the correlation between near-wellbore spatial properties (e.g., porosity, permeability, pressure, and saturation) and cumulative oil production as inputs and output, respectively. The learned M-CNN predicts oil productivity at every candidate well location and selects qualified well placement scenarios. The prediction performance of the M-CNN for hydrocarbon-prolific regions is improved by adding qualified scenarios to the learning data and re-training the M-CNN. This iterative learning scheme enhances the suitability of the proxy for solving the problem of maximizing oil productivity. The validity of the proxy is tested with a benchmark model, UNISIM-I-D, in which four oil production wells are sequentially drilled. The M-CNN approach demonstrates remarkable consistency and alignment with full-physics reservoir simulation results. It achieves prediction accuracy within a 3% relative error margin, while significantly reducing computational costs to just 11.18% of those associated with full-physics reservoir simulations. Moreover, the M-CNN-optimized well placement strategy yields a substantial 47.40% improvement in field cumulative oil production compared to the original configuration. These findings underscore the M-CNN’s effectiveness in sequential well placement optimization, striking an optimal balance between predictive accuracy and computational efficiency. The method’s ability to dramatically reduce processing time while maintaining high accuracy makes it a valuable tool for enhancing oil field productivity and streamlining reservoir management decisions.

Flood Mapping Methodologies in Google Earth Engine Using Optical and Radar Data: A Comparative Study

Floods are among the most severe and frequent natural disasters, impacting numerous countries worldwide. This study investigates flood mapping methodologies utilizing Google Earth Engine (GEE) with Sentinel-1, Sentinel-2, and Landsat data, focusing on the January 2021 Tetouan flood in Morocco. Three approaches were assessed: Sentinel-1 thresholding and NDWI (Normalized Difference Water Index) methods applied to Sentinel-2 and Landsat imagery. The analysis revealed flooded areas of 891 hectares (Sentinel-1), 814 hectares (Sentinel-2), and 1237 hectares (Landsat), validated against ArcGIS (Geographic Information System) results estimating 900 hectares. Sentinel-1 demonstrated superior accuracy with only a 9-hectare deviation and proved effective under cloudy conditions. Sentinel-2 provided a balance between spatial resolution and error levels, with moderate commission and omission errors. Landsat detected the largest flood extent but exhibited a slight overestimation. The study emphasizes the advantages of GEE’s cloud-based platform, which significantly reduced processing time, facilitating rapid flood extent mapping. This scalability and efficiency make GEE an invaluable tool for disaster management. The results underline the potential of these methodologies for accurate and timely flood monitoring, enabling informed decision-making in resilience planning and emergency response. Such advancements are critical for mitigating the impacts of flooding and supporting sustainable disaster management strategies in vulnerable regions worldwide.

THE METHOD OF ADAPTIVE STATISTICAL CODING TAKING INTO ACCOUNT THE STRUCTURAL FEATURES OF VIDEO IMAGES

The paper proposes a method of improved adaptive integral arithmetic coding. This method is advisable to use in the technology of multi-level processing of video data based on the JPEG method. The technology is based on the detection of key information at several stages of video data processing. To reduce the output volume, the RLE algorithm and integral arithmetic coding are adapted to the new structure of the input data. Thus, the method of linearization of two-dimensional transformants based on zig-zag scanning was further developed. The differences of the method consist in carrying out vector intertransformation zig-zag linearization taking into account the selection of spectral components defined as complementary. The linearized decomposition approach was developed for the first time transformants based on entry into control ranges. In connection with the presence of different types of transformants in the group, the threshold is adapted according to the criterion of the total uneven number of non-equilibrium complementary components. On the basis of taking into account the probability of occurrence of dictionary elements, integrated arithmetic coding (two-dictionary integrated arithmetic coding) has been improved. Determination of current code components according to the decomposed working interval depending on the power of the dictionaries of significant elements and the number of repetitions. This allows you to additionally take into account the statistical features of the components of the RLE-structured linearized transformants and reduce the length of the arithmetic code; for the first time, a transformant compression method was created based on the reduction of various types of redundancy in groups of transformants. Comparative experimental analysis with known methods indicated that the developed technology has a higher compression ratio with reduced processing time. This makes it possible to ensure the necessary level of access and reliability in the conditions of the growth of the original volume of data.

Enhancing Big Data Processing Efficiency in AI-Based Healthcare Systems: A Comparative Analysis of Random Forest and Deep

This research focuses on optimizing the speed of Big Data processing using Artificial Intelligence (AI) in healthcare applications. The study integrates Random Forest (RF) and Deep Learning (DL) algorithms with cloud-based computing systems to improve data processing efficiency. The dataset includes both structured data, such as Electronic Health Records (EHR), and unstructured data, like medical images. The results show that RF performs better with structured data, achieving a lower Mean Squared Error (MSE) and higher R-squared (R²) than traditional methods. Meanwhile, DL achieves superior accuracy and Area Under the Curve (AUC) in processing unstructured data. By utilizing the distributed computing power of Spark on a cloud platform, the processing speed was significantly enhanced, as demonstrated by a statistically significant reduction in processing time (p < 0.05) observed through a t-test analysis comparing Spark-based computing with traditional methods. Despite these improvements, challenges such as data privacy and infrastructure costs remain. Despite these improvements, challenges such as data privacy and infrastructure costs remain. This research provides a robust framework for real-time healthcare data analysis, highlighting its potential to improve decision-making processes and patient outcomes in medical services.

A Registration Method Based on Ordered Point Clouds for Key Components of Trains.

Point cloud registration is pivotal across various applications, yet traditional methods rely on unordered point clouds, leading to significant challenges in terms of computational complexity and feature richness. These methods often use k-nearest neighbors (KNN) or neighborhood ball queries to access local neighborhood information, which is not only computationally intensive but also confines the analysis within the object's boundary, making it difficult to determine if points are precisely on the boundary using local features alone. This indicates a lack of sufficient local feature richness. In this paper, we propose a novel registration strategy utilizing ordered point clouds, which are now obtainable through advanced depth cameras, 3D sensors, and structured light-based 3D reconstruction. Our approach eliminates the need for computationally expensive KNN queries by leveraging the inherent ordering of points, significantly reducing processing time; extracts local features by utilizing 2D coordinates, providing richer features compared to traditional methods, which are constrained by object boundaries; compares feature similarity between two point clouds without keypoint extraction, enhancing efficiency and accuracy; and integrates image feature-matching techniques, leveraging the coordinate correspondence between 2D images and 3D-ordered point clouds. Experiments on both synthetic and real-world datasets, including indoor and industrial environments, demonstrate that our algorithm achieves an optimal balance between registration accuracy and efficiency, with registration times consistently under one second.

Effective Stemmers Using Trie Data Structure for Enhanced Processing of Gujarati Text

Stemming plays a crucial role in natural language processing and information retrieval. It is challenging for the Gujarati language due to the complex morphology of several stemming algorithms for the Gujarati language that have been developed using rule-based, dictionary-based, or hybrid approaches. However, they are computationally expensive, produce more over-stemming errors and have limited accuracy. This paper introduces three novel optimized Gujarati stemmers using a trie data structure to overcome the above-mentioned limitations. The significant contributions to this paper are as follows. First, three optimized Gujarati stemmers, namely Optimized Gujarati Stemmer using Suffix Stripping Approach (OGS_SSA), Optimized Gujarati Stemmer using Rule-Based Approach (OGS_RBA), and Optimized Gujarati Stemmer using Re-parsing Based Approach (OGS_RPA), are proposed. Second, a novel algorithm to create a Gujarati dictionary using the trie data structure is proposed. Third, the proposed stemmers are rigorously assessed using three standard datasets, namely entertainment, health, and agriculture. The performance of the proposed stemmers is measured using evaluation parameters such as precision, recall, F1 score, accuracy, number of stemming errors and processing time. The results show that OGS_RPA consistently exceeds the OGS_SSA and OGS_RBA for precision, recall, F1 score, and accuracy. In addition, it exhibits a lower number of stemming errors. Moreover, the performance of the proposed stemmer is compared with the existing Gujarati hybrid stemmer. The results show a 14–16% improvement in accuracy and less processing time compared to the Gujarati hybrid stemmer. OGS_SSA demonstrated enhanced processing time, making it a feasible option for applications that prioritize prompt response time. Furthermore, it demonstrates 10–11% enhancement in accuracy and a reduction in processing time than the Gujarati hybrid stemmer. OGS_RBA exhibits moderate performance due to its rule-based methodology compared to OGS_RPA and OGS_SSA. However, it shows 10–13% improvement in accuracy than the Gujarati hybrid stemmer.

Enhancing Big Data Processing Efficiency in AI-Based Healthcare Systems: A Comparative Analysis of Random Forest and Deep

This research focuses on optimizing the speed of Big Data processing using Artificial Intelligence (AI) in healthcare applications. The study integrates Random Forest (RF) and Deep Learning (DL) algorithms with cloud-based computing systems to improve data processing efficiency. The dataset includes both structured data, such as Electronic Health Records (EHR), and unstructured data, like medical images. The results show that RF performs better with structured data, achieving a lower Mean Squared Error (MSE) and higher R-squared (R²) compared to traditional methods. Meanwhile, DL achieves superior accuracy and Area Under the Curve (AUC) in processing unstructured data. By utilizing the distributed computing power of Spark on a cloud platform, the processing speed was significantly enhanced, as demonstrated by a statistically significant reduction in processing time (p < 0.05) observed through a t-test analysis comparing Spark-based computing with traditional methods. Despite these improvements, challenges such as data privacy and infrastructure costs remain. Despite these improvements, challenges such as data privacy and infrastructure costs remain. This research provides a robust framework for real-time healthcare data analysis, highlighting its potential to improve decision-making processes and patient outcomes in medical services.