Advanced Data Processing Research Articles

Multisource Data-Driven Carbon Price Composite Forecasting Model: Based on Feature Selection and Multiscale Prediction Strategy

Accurate prediction of carbon trading prices is crucial for guiding investors to make informed decisions and assisting governments in formulating scientific carbon trading policies. This paper introduces a multisource data-driven carbon price composite forecasting model, aimed at enhancing prediction accuracy through advanced data processing and analysis methods. The model initially employs a secondary decomposition strategy, including Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Variational Mode Decomposition (VMD) methods, to decompose the original data series into three sub-sequences of different frequencies. Subsequently, it utilizes the Partial Autocorrelation Function (PACF) and Random Forest algorithm for feature selection to determine the input variables for different frequency sequences and conducts in-depth analysis and selection of influencing factors, including unstructured data. Furthermore, the model employs a multiscale forecasting strategy, combining Particle Swarm Optimization (PSO) enhanced Bidirectional Long Short-Term Memory (BiLSTM) and Extreme Gradient Boosting (XGBoost) models, along with the Autoregressive Integrated Moving Average (ARIMA) method, to predict based on the characteristics of different frequency components. Finally, the forecasts are integrated using PSO-BiLSTM to form a comprehensive forecast. Notably, given the high correlation between the trend series and influencing factor variables, the model jointly predicts them. A case study based on the Guangdong carbon market in China demonstrates that the proposed composite forecasting model outperforms other benchmark models, with Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) values of 0.4009, 0.2699, and 0.5183%, respectively. This forecasting model provides an effective tool for predicting and analyzing carbon price fluctuations, offering new insights for precise carbon market price predictions.

An IoT Healthcare System With Deep Learning Functionality for Patient Monitoring

ABSTRACTCurrently, healthcare systems operate under conventional management practices and entail storing and processing substantial medical data. Integrating the Internet of Things (IoT) and wireless sensor networks (WSNs) technologies has facilitated the development of IoT‐enabled healthcare, which possesses advanced data processing capabilities and extensive data storage. This paper proposes a WSN and IoT framework for patient monitoring in high‐speed 5G communications. Based on an artificial neural network (ANN), an intelligent health monitoring system was developed using IoT technology to monitor a person's blood pressure, heart rate, oxygen level, and temperature. Furthermore, the system helps the elderly being in critical cases in their homes to communicate and update their medical condition with the hospital, especially in critical cases, to be treated as soon as possible, especially in remote areas. The experimental results showed the superiority and effectiveness of the proposed system. Moreover, relying on ANNs to extract the basic features, the accuracy reached 96%. The proposed system was implemented practically, and the results were displayed in real time and compared with commercial medical devices. Maximum relative errors are heart rate (2.19), body temperature (2.94), systolic blood pressure (3.4), diastolic blood pressure (2.89), and SpO2 (1.05). On the other hand, the proposed system is much faster than other wireless communication methods, regardless of the detection quality.

Quantum Machine Learning for Advanced Data Processing in Business Analytics: A Path Toward Next-Generation Solutions

Quantum Machine Learning (QML) is a rising paradigm of computing that holds high possibilities to revolutionise data analysis in the business analytics industry. This paper aims at presenting how QML can solve the increasingly challenging demands of big contributions to large-scale data analysis in business contexts, achieving better performance than orthodox machine learning methods in terms of time and efficacy. LIQUID: This research utilises actual business data and scenarios and solving problems by using quantum algorithms – VQE and QSVM. At the core of our approach, we perform extensive validation of QML models on platforms such as IBM’s Quantum Experience and D-Wave systems pertaining to critical use cases for businesses would include financial modelling, supply chain management, and customer behaviour prediction. The results presented here suggest that quantum algorithm speeds processing by 30-50% when compared with conventions approaches of computation. Moreover, QML has shown better results for prediction in analytics for various firms and provide them better aptitudes for decision-making. Hence the uniqueness of this research by grounding real world business problems in quantum algorithms and demonstrating empirically how superior they are compared to the classical alternatives in dealing with large datasets. Considering the future of business analytics, QML looks set to be a real game changer for industries that heavily rely on big data analysis. In this it has filled a gap which would cause a scholarly without hard gap between theoretical quantum computing and real business applications.

A critical analysis of the role of artificial intelligence and machine learning in enhancing nuclear waste management

Abstract Controlling and managing nuclear waste is a significant challenge due to the harmful effects of radioactive materials on human health. To address this, long-term storage solutions are essential. Artificial Intelligence (AI) and Machine Learning (ML) are being utilized to make nuclear waste management safer, more effective, and efficient. This paper evaluates various applications of AI and ML in the field of nuclear waste, covering aspects such as predictive maintenance, waste sorting, and classification. AI and ML enhance real-time monitoring of storage conditions and optimize waste handling procedures through advanced data processing capabilities. Implementing cutting-edge solutions is crucial to protect public health and the environment from radioactive waste. The purpose of this evaluation is to examine how AI and ML improve nuclear waste management processes. These technologies can reduce human exposure to harmful materials and increase the safety and efficiency of managing nuclear waste through advanced predictive capabilities. The introduction of AI and ML in nuclear waste management is driving significant changes and innovations, addressing current issues, and establishing new guidelines for future policies.

3D micromorphological reconstruction and roughness characterization of wood surface based on sequence images

A novel non-contact optical inspection technique is proposed to precisely reconstruct the three-dimensional surface structure of wood and evaluate its roughness. The feasibility of using image fusion techniques to characterize the 3D roughness of wood surfaces is explored by combining high-resolution serial image acquisition techniques with advanced data processing methods. The work focuses on examining various cut surfaces of three distinct wood species: Larch, Catalpa, and Toona sinensis. The proposed 3D roughness parameters are verified using 3D reconstruction and precise measurements. The experimental results demonstrate that the proposed method exhibits strong adaptability in measuring wood surface roughness and achieves a high degree of consistency with the results obtained from traditional digital microscope systems. This study not only validates the possible use of multilayer sequence image fusion technology in measuring wood roughness, but also establishes a solid basis for the creation of 3D assessment criteria for wood surface roughness and associated inspection systems.

COMPARISON OF NAÏVE BAYES AND K-NEAREST NEIGHBOR MODELS FOR IDENTIFYING THE HIGHEST PREVALENCE OF STUNTING CASES IN EAST JAVA

Indonesia will experience a demographic bonus in 2030, where the productive age group will dominate the population and become a buffer for the economy. However, this potential is in vain if human resources experience stunting. According to WHO (2015), stunting is a disorder of child growth and development due to chronic malnutrition and repeated infections, characterized by below-standard length or height. Based on the background of the problem, the author wants to compare the prediction of the prevalence of the highest stunting cases in East Java using the Naive Bayes method and the K-Nearest Neighbor method. The stages carried out in this study are data collection, initial data processing, advanced data processing using the Naïve Bayes Method and K-Nearest Neighbor, and comparative analysis. The results of the implementation of the Naïve Bayes and K-Nearest Neighbor methods are in the form of stunting prevalence prediction charts with variables that affect LBW and TTD. The results of simulations conducted in 6 regions, the Naive Bayes method gets the highest accuracy value of 83.33% in simulation one and 66.67%. The smallest RMSE value is 0.382 simulation 1 and 0.469 simulation 2. This shows that the Naive Bayes method can predict well.

Assessment of ChatGPT-4 in Family Medicine Board Examinations Using Advanced AI Learning and Analytical Methods: Observational Study.

This research explores the capabilities of ChatGPT-4 in passing the American Board of Family Medicine (ABFM) Certification Examination. Addressing a gap in existing literature, where earlier artificial intelligence (AI) models showed limitations in medical board examinations, this study evaluates the enhanced features and potential of ChatGPT-4, especially in document analysis and information synthesis. The primary goal is to assess whether ChatGPT-4, when provided with extensive preparation resources and when using sophisticated data analysis, can achieve a score equal to or above the passing threshold for the Family Medicine Board Examinations. In this study, ChatGPT-4 was embedded in a specialized subenvironment, "AI Family Medicine Board Exam Taker," designed to closely mimic the conditions of the ABFM Certification Examination. This subenvironment enabled the AI to access and analyze a range of relevant study materials, including a primary medical textbook and supplementary web-based resources. The AI was presented with a series of ABFM-type examination questions, reflecting the breadth and complexity typical of the examination. Emphasis was placed on assessing the AI's ability to interpret and respond to these questions accurately, leveraging its advanced data processing and analysis capabilities within this controlled subenvironment. In our study, ChatGPT-4's performance was quantitatively assessed on 300 practice ABFM examination questions. The AI achieved a correct response rate of 88.67% (95% CI 85.08%-92.25%) for the Custom Robot version and 87.33% (95% CI 83.57%-91.10%) for the Regular version. Statistical analysis, including the McNemar test (P=.45), indicated no significant difference in accuracy between the 2 versions. In addition, the chi-square test for error-type distribution (P=.32) revealed no significant variation in the pattern of errors across versions. These results highlight ChatGPT-4's capacity for high-level performance and consistency in responding to complex medical examination questions under controlled conditions. The study demonstrates that ChatGPT-4, particularly when equipped with specialized preparation and when operating in a tailored subenvironment, shows promising potential in handling the intricacies of medical board examinations. While its performance is comparable with the expected standards for passing the ABFM Certification Examination, further enhancements in AI technology and tailored training methods could push these capabilities to new heights. This exploration opens avenues for integrating AI tools such as ChatGPT-4 in medical education and assessment, emphasizing the importance of continuous advancement and specialized training in medical applications of AI.

An innovative attention infused- BiRecurrenTwin network assisted hybrid segmentation technique for accurate heart disease prediction

Heart disease is a noteworthy global health concern, profoundly affecting public health and individual well-being. Early prediction and diagnosis are crucial for reducing its negative impact. This work focuses on developing an effectual heart disease detection employing advanced optimization approaches and data processing. The proposed system incorporates a hybrid segmentation algorithm, Hybrid K-means-Fuzzy-C-means (HKMFCM) clustering, which assigns membership degrees to data points, enabling soft clustering and accommodating data uncertainty. Additionally, the Artificial Bee Colony (ABC) Optimization method is applied for feature selection, mimicking the foraging behavior of honeybees to identify the most discriminative attributes from the dataset. This optimization algorithm iteratively explores the feature space to select features that enhance the model's predictive accuracy. Furthermore, a novel classification architecture, termed the Attention-infused BiRecurrenTwin Network, is introduced to accurately predict heart disease based on segmented and extracted patient data profiles. This classifier leverages both Bidirectional Gated Recurrent Unit (BiGRU) and Bidirectional Long Short-Term Memory (BiLSTM) networks, with their bidirectional nature capturing both past and future contexts, thus increasing the classifier's capability to detect subtle temporal patterns in patient data. In addition, the proposed system addresses traditional approaches limitations through its advanced components like HKMFCM (effectively manages data uncertainty by enabling soft clustering), ABC Optimization technique (enabling an iterative, global search for the most discriminative attributes) Attention-infused BiRecurrenTwin Network (surpasses conventional classifiers by capturing both past and future temporal patterns in patient data). The simulation outcomes demonstrate that the developed system attains improved performance, with accuracy, ROC, F-measure, precision, recall, sensitivity, and specificity values of 96.09%, 97%, 95%, 96.6%, 94.3%, 95.14%, and 97.05%, respectively which is higher than the baseline models with an average of 7.75 % increase in accuracy. These results indicate that the developed predictive models show promise in accurately classifying individuals based on their extracted features, thereby facilitating the early recognition of heart disease.

Application of vibration signals in railway track diagnostics using a mobile railway platform

The article presents a comprehensive method for using vibration signals to diagnose railway tracks. The primary objective is to gather detailed information on track conditions through a passive experiment. This involves using mobile diagnostic tools and techniques to assess railway infrastructure. The article elaborates on the range of diagnostic activities conducted in accordance with detailed railway regulations and highlights the benefits and capabilities of mobile diagnostics in railway transport. The research includes mobile field measurements across the general railway manager’s network, employing vibration signals to detect and evaluate track conditions. The methodology section provides a thorough description of the mobile measurement rail platform, detailing the equipment used, the routes taken for measurements, and the processes of data acquisition and processing. The data obtained from these measurements is crucial for understanding the actual technical condition of the railway tracks. The method of obtaining and processing data is explained in relation to the real technical condition of the railway track. This involves using transducers with specific parameters and parametrically defined signal recording, along with dedicated analysis techniques in post-processing. Vibration signals serve as the primary carrier of information in this diagnostic method. The article details the step-by-step procedures for collecting and analyzing these signals to provide accurate assessments of track conditions. Based on the results from the mobile measurement rail platform, the article characterizes various areas of diagnostics where vibration signals are particularly effective for technical evaluation. These areas include identifying track defects, monitoring track surface and railway crossing and assessing the overall structural health of the railway infrastructure. The use of vibration signals offers a non-invasive and efficient means of track diagnostics, providing real-time data for maintenance and repair decisions. In conclusion, the article underscores the significance of mobile diagnostics in enhancing the safety and reliability of railway transport. By leveraging vibration signals and advanced data processing techniques, this method provides a framework for continuous monitoring and assessment of railway track conditions, ultimately contributing to improved maintenance strategies and operational efficiency.

Advanced Sensor Technologies in CAVs for Traditional and Smart Road Condition Monitoring: A Review

This paper explores new sensor technologies and their integration within Connected Autonomous Vehicles (CAVs) for real-time road condition monitoring. Sensors like accelerometers, gyroscopes, LiDAR, cameras, and radar that have been made available on CAVs are able to detect anomalies on roads, including potholes, surface cracks, or roughness. This paper also describes advanced data processing techniques of data detected with sensors, including machine learning algorithms, sensor fusion, and edge computing, which enhance accuracy and reliability in road condition assessment. Together, these technologies support instant road safety and long-term maintenance cost reduction with proactive maintenance strategies. Finally, this article provides a comprehensive review of the state-of-the-art future directions of condition monitoring systems for traditional and smart roads.

Monitoring the gas metal arc additive manufacturing process using unsupervised machine learning

The study aimed to assess the performance of several unsupervised machine learning (ML) techniques in online anomaly (The term “anomaly” is used here to indicate a departure from expected process behavior which may indicate a quality issue which requires further investigation. The term “defect detection” has often been used previously but the specific imperfection is often indirectly inferred.) detection during surface tension transfer (STT)-based wire arc additive manufacturing. Recent advancements in quality monitoring for wire arc manufacturing were reviewed, followed by a comparison of unsupervised ML techniques using welding current and welding voltage data collected during a defect-free deposition process. Both time domain and frequency domain feature extraction techniques were applied and compared. Three analysis methodologies were adopted: ML algorithms such as isolation forest, local outlier factor, and one-class support vector machine. The results highlight that incorporating frequency analysis, such as fast Fourier transform (FFT) and discrete wavelet transform (DWT), for feature extraction based on general frequency response and defined bandwidth frequency response, significantly improves performance, reflected in a 14% increase in F2 score, compared with time-domain features extraction. Additionally, a deep learning approach employing a convolutional autoencoder (CAE) demonstrated superior performance by processing time-frequency domain data stored as spectrograms obtained through short-time Fourier transform (STFT) analysis. The CAE method outperformed frequency domain analysis and traditional ML approaches, achieving an additional 5% improvement in F2-score. Notably, the F2-score (The F2 score is the weighted harmonic mean of the precision and recall (given a threshold value). Unlike the F1 score, which gives equal weight to precision and recall, the F2 score gives more weight to recall than to precision.) increased significantly from 0.78 in time domain analysis to 0.895 in time-frequency analysis. The study emphasizes the potential of utilizing low-cost sensors to develop anomaly detection modules with enhanced accuracy. These findings underscore the importance of incorporating advanced data processing techniques in wire arc additive manufacturing for improved quality control and process optimization.

Exploring the Association between Pro-Inflammation and the Early Diagnosis of Alzheimer’s Disease in Buccal Cells Using Immunocytochemistry and Machine Learning Techniques

The progressive aging of the global population and the high impact of neurodegenerative diseases, such as Alzheimer’s disease (AD), underscore the urgent need for innovative diagnostic and therapeutic strategies. AD, the most prevalent neurodegenerative disorder among the elderly, is expected to affect 75 million people in developing countries by 2030. Despite extensive research, the precise etiology of AD remains elusive due to its heterogeneity and complexity. The key pathological features of AD, including amyloid-beta plaques and hyperphosphorylated tau protein, are established years before clinical symptoms appear. Recent studies highlight the pivotal role of neuroinflammation in AD pathogenesis, with the chronic activation of the brain’s immune system contributing to the disease’s progression. Pro-inflammatory cytokines, such as TNF-α, IL-1β, and IL-6, are elevated in AD and mild cognitive impairment (MCI) patients, suggesting a strong link between peripheral inflammation and CNS degeneration. There is a pressing need for minimally invasive, cost-effective diagnostic methods. Buccal mucosa cells and saliva, which share an embryological origin with the CNS, show promise for AD diagnosis and prognosis. This study integrates cellular observations with advanced data processing and machine learning to identify significant biomarkers and patterns, aiming to enhance the early diagnosis and prevention strategies for AD.

Feedback system for reactor process analysis

The article discusses an approach to analyzing processes in industrial reactors using advanced systems with feedback. The authors describe the system preparation and image reconstruction algorithms of ultrasonic tomographs (USTs) that have applications in industry. The research presented in this paper focuses on developing effective strategies for controlling and monitoring chemical reaction processes in reactors. Using advanced data processing techniques, the authors propose systems with feedback that enable accurate analysis and optimization of reactor operating conditions. A key aspect is ultrasonic tomographic imaging, which provides precise data on the state of the process in the reactor. In summary, the paper presents a state-of-the-art approach to analyzing chemical reaction processes in industrial reactors using advanced feedback systems and ultrasonic imaging technologies. The proposed solutions are essential for improving efficiency and process control in the chemical industry.

Drone Technology for Precision Agriculture: Advancements and Optimization Strategies

This paper delves into the development and optimization of an intelligent agricultural monitoring system that makes use of drone technology to enhance agricultural productivity and sustainability. With the world's population on the rise and the scarcity of arable land, precision agriculture becomes essential in guaranteeing food security. By harnessing state-of-the-art sensors and imaging technologies, drone technology offers a new and innovative approach to agricultural monitoring. Efficiently collecting vital data on vegetation indices, soil moisture, and crop health. This study seeks to create a state-of-the-art drone-based monitoring system that uses advanced machine learning algorithms and data processing technologies to analyze agricultural data with exceptional precision. It explores the most efficient methods for operating drones, including flight planning and data collection protocols, with the aim of creating a comprehensive agricultural monitoring system. This platform provides the convenience of automating monitoring processes, leading to lower labor costs, improved resource allocation, and a beneficial impact on agricultural modernization. The article delves into the effects of the latest developments in drone technology and the subsequent decrease in costs on the agriculture industry worldwide. It highlights the ways in which these advancements are transforming conventional farming methods.

AI-Driven Financial Modeling Techniques: Transforming Investment Strategies

Artificial Intelligence (AI) has revolutionized financial modeling and investment strategies by introducing sophisticated algorithms and advanced data processing capabilities. This article delves into a variety of AI-driven financial modeling techniques, such as machine learning, natural language processing, and deep learning, providing detailed examples of their applications. These techniques are shown to significantly enhance predictive accuracy, risk management, portfolio optimization, and trading strategies. Through case studies and empirical evidence, the article highlights the transformative impact of AI on financial modeling. Additionally, it addresses the challenges in implementing AI-driven models, such as data quality issues, model interpretability, and regulatory concerns, and identifies future research opportunities to further advance the field. The comprehensive analysis provided offers a clear understanding of how AI is reshaping the financial industry, the potential benefits it brings, and the hurdles that must be overcome to fully harness its capabilities.

Enhancing Hospital Efficiency through IoT and AI: A Smart Healthcare System

In the rapidly evolving healthcare landscape, the integration of Internet of Things (IoT) and Artificial Intelligence (AI) is transforming hospital efficiency. This study explores how these technologies can enhance hospital operations by optimizing resource management, improving patient care, and reducing operational costs. IoT devices enable real-time monitoring of patient health and hospital assets, facilitating timely interventions and maintenance. Concurrently, AI-driven analytics improve decision-making processes by predicting patient needs and optimizing resource allocation. The synergy between IoT and AI creates a smart healthcare system that offers advanced data processing and actionable insights, leading to improved patient outcomes. Despite challenges such as data privacy concerns and infrastructure investments, the potential benefits of IoT and AI in healthcare are substantial. This paper presents a comprehensive framework for integrating these technologies into hospital operations, highlighting their impact on efficiency and patient care. The findings suggest that IoT and AI can significantly enhance hospital performance, paving the way for a smarter healthcare system.

Raman spectroscopy - a visit to the literature on plant, food, and agricultural studies.

Raman spectroscopy, a fast, non-invasive, and label-free optical technique, has significantly advanced plant and food studies and precision agriculture by providing detailed molecular insights into biological tissues. Utilizing the Raman scattering effect generates unique spectral fingerprints that comprehensively analyze tissue composition, concentration, and molecular structure. These fingerprints are obtained without chemical additives or extensive sample preparation, making Raman spectroscopy particularly suitable for in-field applications. Technological enhancements such as surface-enhanced Raman scattering, Fourier-transform-Raman spectroscopy, and chemometrics have increased Raman spectroscopy sensitivity and precision. These and other advancements enable real-time monitoring of compound translocation within plants and improve the detection of chemical and biological contaminants, essential for food safety and crop optimization. Integrating Raman spectroscopy into agronomic practices is transformative and marks a shift toward more sustainable farming activities. It assesses crop quality - as well as the quality of the food that originated from crop production - early plant stress detection and supports targeted breeding programs. Advanced data processing techniques and machine learning integration efficiently handle complex spectral data, providing a dynamic and detailed view of food conditions and plant health under varying environmental and biological stresses. As global agriculture faces the dual challenges of increasing productivity and sustainability, Raman spectroscopy stands out as an indispensable tool, enhancing farming practices' precision, food safety, and environmental compatibility. This review is intended to select and briefly comment on outstanding literature to give researchers, students, and consultants a reference for works of literature in Raman spectroscopy mainly focused on plant, food, and agronomic sciences. © 2024 Society of Chemical Industry.

Crucial future observations and directions for unveiling magnetopause dynamics and their geospace impacts

The dynamics of Earth’s magnetopause, driven by several different external/internal physical processes, plays a major role in the geospace energy budget. Given magnetopause motion couples across many space plasma regions, numerous forms of observations may provide valuable information in understanding these dynamics and their impacts. In-situ multi-point spacecraft measurements measure the local plasma environment, dynamics and processes; with upcoming swarms providing the possibility of improved spatiotemporal reconstruction of dynamical phenomena, and multi-mission conjunctions advancing understanding of the “mesoscale” coupling across the geospace “system of systems.” Soft X-ray imaging of the magnetopause should enable boundary motion to be directly remote sensed for the first time. Indirect remote sensing capabilities might be enabled through the field-aligned currents associated with disturbances to the magnetopause; by harnessing data from satellite mega-constellations in low-Earth orbit, and taking advantage of upgraded auroral imaging and ionospheric radar technology. Finally, increased numbers of closely-spaced ground magnetometers in both hemispheres may help discriminate between high-latitude processes in what has previously been a “zone of confusion.” Bringing together these multiple modes of observations for studying magnetopause dynamics is crucial. These may also be aided by advanced data processing techniques, such as physics-based inversions and machine learning methods, along with comparisons to increasingly sophisticated geospace assimilative models and simulations.

Localization and segmentation of atomic columns in supported nanoparticles for fast scanning transmission electron microscopy

To accurately capture the dynamic behavior of small nanoparticles in scanning transmission electron microscopy, high-quality data and advanced data processing is needed. The fast scan rate required to observe structural dynamics inherently leads to very noisy data where machine learning tools are essential for unbiased analysis. In this study, we develop a workflow based on two U-Net architectures to automatically localize and classify atomic columns at particle-support interfaces. The model is trained on non-physical image simulations, achieves sub-pixel localization precision, high classification accuracy, and generalizes well to experimental data. We test our model on both in situ and ex situ experimental time series recorded at 5 frames per second of small Pt nanoparticles supported on CeO2(111). The processed movies show sub-second dynamics of the nanoparticles and reveal site-specific movement patterns of individual atomic columns.

Addressing Demographic Bias in Age Estimation Models through Optimized Dataset Composition

Bias in facial recognition systems often results in unequal performance across demographic groups. This study addresses this by investigating how dataset composition affects the performance and bias of age estimation models across ethnicities. We fine-tuned pre-trained Convolutional Neural Networks (CNNs) like VGG19 on the diverse UTKFace dataset (23,705 samples: 10,078 White, 4526 Black, 3434 Asian) and APPA-REAL (7691 samples: 6686 White, 231 Black, 674 Asian). Our approach involved adjusting dataset compositions by oversampling minority groups or reducing samples from overrepresented groups to mitigate bias. We conducted experiments to identify the optimal dataset composition that minimizes performance disparities among ethnic groups. The primary performance metric was Mean Absolute Error (MAE), measuring the average magnitude of prediction errors. We also analyzed the standard deviation of MAE across ethnic groups to assess performance consistency and equity. Our findings reveal that simple oversampling of minority groups does not ensure equitable performance. Instead, systematic adjustments, including reducing samples from overrepresented groups, led to more balanced performance and lower MAE standard deviations across ethnicities. These insights highlight the importance of tailored dataset adjustments and suggest exploring advanced data processing methods and algorithmic tweaks to enhance fairness and accuracy in facial recognition technologies.