Data Quality Research Articles

Predictive modeling and anomaly detection in large-scale web portals through the CAWAL framework

This study presents an approach that uses session and page view data collected through the CAWAL framework, enriched through specialized processes, for advanced predictive modeling and anomaly detection in web usage mining (WUM) applications. Traditional WUM methods often rely on web server logs, which limit data diversity and quality. Integrating application logs with web analytics, the CAWAL framework creates comprehensive session and page view datasets, providing a more detailed view of user interactions and effectively addressing these limitations. This integration enhances data diversity and quality while eliminating the preprocessing stage required in conventional WUM, leading to greater process efficiency. The enriched datasets, created by cross-integrating session and page view data, were applied to advanced machine learning models, such as Gradient Boosting and Random Forest, which are known for their effectiveness in capturing complex patterns and modeling non-linear relationships. These models achieved over 92% accuracy in predicting user behavior and significantly improved anomaly detection capabilities. The results show that this approach offers detailed insights into user behavior and system performance metrics, making it a reliable solution for improving large-scale web portals’ efficiency, reliability, and scalability.

FedFAIM: A Model Performance-Based Fair Incentive Mechanism for Federated Learning

Federated Learning (FL) has emerged as a privacy-preserving distributed machine learning paradigm. To motivate data owners to contribute towards FL, research on FL incentive mechanisms is gaining great interest. Existing monetary incentive mechanisms generally share the same FL model with all participants regardless of their contributions. Such an assumption can be unfair towards participants who contributed more and promote undesirable free-riding, especially when the final model is of great utility value to participants. In this paper, we propose a Fairness-Aware Incentive Mechanism for federated learning (FedFAIM) to address such problem. It satisfies two types of fairness notion: 1) aggregation fairness, which determines aggregation results according to data quality; 2) reward fairness, which assigns each participant a unique model with performance reflecting his contribution. Aggregation fairness is achieved through efficient gradient aggregation which examines local gradient quality and aggregates them based on data quality. Reward fairness is achieved through an efficient Shapley value-based contribution assessment method and a novel reward allocation method based on reputation and distribution of local and global gradients. We further prove reward fairness is theoretically guaranteed. Extensive experiments show that FedFAIM provides stronger incentives than similar non-monetary FL incentive mechanisms while achieving a high level of fairness.

Advances in Protein-Ligand Binding Affinity Prediction via Deep Learning: A Comprehensive Study of Datasets, Data Preprocessing Techniques, and Model Architectures.

Drug discovery is a complex and expensive procedure involving several timely and costly phases through which new potential pharmaceutical compounds must pass to get approved. One of these critical steps is the identification and optimization of lead compounds, which has been made more accessible by the introduction of computational methods, including deep learning (DL) techniques. Diverse DL model architectures have been put forward to learn the vast landscape of interaction between proteins and ligands and predict their affinity, helping in the identification of lead compounds. This survey fills a gap in previous research by comprehensively analyzing the most commonly used datasets and discussing their quality and limitations. It also offers a comprehensive classification of the most recent DL methods in the context of protein-ligand binding affinity prediction (BAP), providing a fresh perspective on this evolving field. We thoroughly examine commonly used datasets for BAP and their inherent characteristics. Our exploration extends to various preprocessing steps and DL techniques, including graph neural networks, convolutional neural networks, and transformers, which are found in the literature. We conducted extensive literature research to ensure that the most recent deep learning approaches for BAP were included by the time of writing this manuscript. The systematic approach used for the present study highlighted inherent challenges to BAP via DL, such as data quality, model interpretability, and explainability, and proposed considerations for future research directions. We present valuable insights to accelerate the development of more effective and reliable DL models for BAP within the research community. The present study can considerably enhance future research on predicting affinity between protein and ligand molecules, hence further improving the overall drug development process.

The retrospective double-entry of a long-term ecological dataset

Research data are almost always assumed to be reliable, but there are many reasons why data can be unreliable. Manual data-entry error rates are typically observed in the 1 to 4 % range and can be statistically impactful. This has encouraged techniques to mitigate the risk of transcription error, among which the double-entry method remains the most effective. Unfortunately, these techniques are rarely applied retrospectively to datasets collected years or decades ago, including to highly valued long-term ecological datasets that continue to contribute to active research.This study defines an approach for the retrospective double-entry of long-term ecological datasets and then applies it to one such dataset: the 34-year (and counting) Mt Mary Lizard Survey. Software was used to execute comparisons of c.760,000 individual data value pairs across c.56,000 records to corroborate matching values and identify unmatched values.The key findings are: a) from 760,967 value pair comparisons between the originally keyed dataset and a retrospectively re-keyed version of the same dataset, 18,637 differences (2.5 %) were detected, b) almost half (48 %) of the differences detected were intentional alterations made to the original dataset during data curation efforts, c) data differences were not uniformly distributed across data fields but concentrated in the animal identity data field, and d) a three-way comparison of the identity field corroborated a recorded value in almost all cases.Landmark, long-term ecological studies continue to be the evidentiary framework for ecological science. However, data quality metrics—including how faithfully digital transcriptions represent the originally recorded values—are rarely reported. Given that manual transcription errors are virtually assured and the realistic possibility of post hoc, intentional alterations made during data curation, one could legitimately ask whether a manually transcribed and curated dataset is a genuine representation of the originally recorded values. The retrospective double-entry approach is one way to find out.

Multi 2D-CNN-based model for short-term PV power forecast embedded with Laplacian Attention

Amid the bloom of Renewable energy (RE) integrated into the grid, an accurate Photovoltaic(PV) power forecast is considered to be a crucial task in maintaining the reliability and stability of the power systems since this technology strongly depends on various external factors, causing the fluctuation in the output power. However, the poor quality of input data, which is very common in practical circumstances owing to the low-cost measurement and data acquisition devices, poses an enormous challenge for the predictive model to deeply extract the spatial and temporal correlation of the input data. This study proposes a Multi Two-Dimensional Convolutional Neural Network (2D-CNN) for short-term PV power forecast embedded with Laplacian Attention mechanism. By viewing the input sequences in a 2D form, the input map is constructed, and the interconnected feature among variables can be captured by convolution operation. Moreover, with the multiple CNN layers working in parallel architecture, different representations hidden inside the input map can be detected, enabling the proposed model to bring out promising performance across forecast time-step without modifying its initial parameters. In order to reduce the decay impact of irrelevant variables existing inside the input data, the Laplacian Attention mechanism is employed. The Attention matrix is dynamically modified during the training process to produce an accurate attention matrix, which represents the correlation between variables. Therefore, the model is able to focus on informative features and ignore negative ones. The experiments conducted on two different datasets with opposite characteristics provide deep insights into the strength of the proposed model over the baseline model, which strongly demonstrates the efficiency of the proposed model, especially when dealing with datasets bearing tough characteristics.

Vehicle trajectory dataset from drone videos including off-ramp and congested traffic – Analysis of data quality, traffic flow, and accident risk

Vehicle trajectory data have become essential for many research fields, such as traffic flow, traffic safety, and automated driving. To make trajectory data useable for researchers, an overview of the included road section and traffic situation as well as a description of the data processing methodology is necessary. In this paper, we present a trajectory dataset from a German highway with two lanes per direction, an off-ramp and congested traffic in one direction, and an on-ramp in the other direction. The dataset contains 8,648 trajectories and covers 87 ​min and an ∼1,200 ​m long section of the road. The trajectories were extracted from drone videos using a posttrained YOLOv5 object detection model and projected onto the road surface via three-dimensional (3D) camera calibration. The postprocessing methodology can compensate for most false detections and yield accurate speeds and accelerations. The trajectory data are also compared with induction loop data and vehicle-based smartphone sensor data to evaluate the plausibility and quality of the trajectory data. The deviations of the speeds and accelerations are estimated at 0.45 ​m/s and 0.3 ​m/s2, respectively. We also present some applications of the data, including traffic flow analysis and accident risk analysis.

3D point cloud regularization method for uniform mesh generation of mining excavations

Mine excavation systems are usually dozens of kilometers long with varying geometry on a small scale (roughness and shape of the walls) and on a large scale (varying widths of the tunnels, turns, and crossings). In this article, the authors address the problem of analyzing laser scanning data from large mining structures that can be used for various purposes, with focus on ventilation simulations. Together with the quality of the measurement data (diverse point-cloud density, missing samples, holes induced by obstructions in the field of view, measurement noise), this creates problems that require multi-stage processing of the obtained data. The authors propose a robust methodology to process a single segmented section of the mining system. The presented approach focuses on obtaining a point cloud ready for application in the computational fluid dynamics (CFD) analysis of airflow with minimal need for additional manual corrections on the generated mesh model. This requires the point cloud to have evenly distributed points and reduced noise (together with removal of objects inside) while keeping the unique geometrical properties and shape of the scanned tunnels. Proposed methodology uses trajectory of the excavation either obtained during the measurements or by skeletonization process explained in the article. Cross-sections obtained on planes perpendicular to the trajectory are processed towards the equalization of point distribution, removing measurement noise, holes in the point cloud and objects inside the excavation. The effects of the proposed algorithm are validated by comparing the processed cloud with the original cloud and testing within the CFD environment. The algorithm proved high effectiveness in improving skewness rate of the obtained mesh and geometry mapping accuracy (standard deviation below 5 centimeters in cloud-to-mesh comparison).

Interoperable information modelling leveraging asset administration shell and large language model for quality control toward zero defect manufacturing

In the era of Industry 4.0, Zero Defect Manufacturing (ZDM) has emerged as a prominent strategy for quality improvement, emphasizing data-driven approaches for defect prediction, prevention, and mitigation. The success of ZDM heavily depends on the availability and quality of data typically collected from diverse and heterogeneous sources during production and quality control, presenting challenges in data interoperability. Addressing this, we introduce a novel approach leveraging Asset Administration Shell (AAS) and Large Language Models (LLMs) for creating interoperable information models that incorporate semantic contextual information to enhance the interoperability of data integration in the quality control process. AAS, initiated by German industry stakeholders, shows a significant advancement in information modeling, blending ontology and digital twin concepts for the virtual representation of assets. In this work, we develop a systematic, use-case-driven methodology for AAS-based information modeling. This methodology guides the design and implementation of AAS models, ensuring model properties are presented in a unified structure and reference external standardized vocabularies to maintain consistency across different systems. To automate this referencing process, we propose a novel LLM-based algorithm to semantically search model properties within a standardized vocabulary repository. This algorithm significantly reduces manual intervention in model development. A case study in the injection molding domain demonstrates the practical application of our approach, showcasing the integration and linking of product quality and machine process data with the help of the developed AAS models. Statistical evaluation of our LLM-based semantic search algorithm confirms its efficacy in enhancing data interoperability. This methodology offers a scalable and adaptable solution for various industrial use cases, promoting widespread data interoperability in the context of Industry 4.0.

Deep-learning and data-resampling: A novel approach to predict cyanobacterial alert levels in a reservoir

The proliferation of harmful algal blooms results in adverse impacts on aquatic ecosystems and public health. Early warning system monitors algal bloom occurrences and provides management strategies for promptly addressing high-concentration algal blooms following their occurrence. In this study, we aimed to develop a proactive prediction model for cyanobacterial alert levels to enable efficient decision-making in management practices. We utilized 11 years of water quality, hydrodynamic, and meteorological data from a reservoir that experiences frequent harmful cyanobacterial blooms in summer. We used these data to construct a deep-learning model, specifically a 1D convolution neural network (1D-CNN) model, to predict cyanobacterial alert levels one week in advance. However, the collected distribution of algal alert levels was imbalanced, leading to the biased training of data-driven models and performance degradation in model predictions. Therefore, an adaptive synthetic sampling method was applied to address the imbalance in the minority class data and improve the predictive performance of the 1D-CNN. The adaptive synthetic sampling method resolved the imbalance in the data during the training phase by incorporating an additional 156 and 196 data points for the caution and warning levels, respectively. The selected optimal 1D-CNN model with a filter size of 5 and comprising 16 filters achieved training and testing prediction accuracies of 97.3% and 85.0%, respectively. During the test phase, the prediction accuracies for each algal alert level (L-0, L-1, and L-2) were 89.9%, 79.2%, and 71.4%, respectively, indicating reasonably consistent predictive results for all three alert levels. Therefore, the use of synthetic data addressed data imbalances and enhanced the predictive performance of the data-driven model. The reliable forecasts produced by the improved model can support the development of management strategies to mitigate harmful algal blooms in reservoirs and can aid in building an early warning system to facilitate effective responses.

Seasonal pattern of diel variability of CO2 efflux from a large eutrophic lake

Lake is commonly acknowledged as a contributor to atmospheric CO2. Current manual sampling for estimations of CO2 emissions from lakes predominantly relies on daytime CO2 efflux (FCO2) assessments, which tends to overlook the diel variability of FCO2. This potentially introduces bias into CO2 emission estimates. The magnitude of diel FCO2 difference between seasons and the relative importance of underlying drivers in large eutrophic lakes remain inadequately explored. Here, we estimated FCO2 based on the water quality and meteorological data from Lake Taihu, a large eutrophic lake in China, with a temporal resolution of 4 h throughout the year 2021. The lake was a CO2 source with an efflux of 0.56 ± 0.66 mmol C/m2/h. We observed a 14.07 % increase in nocturnal FCO2 compared to daytime levels annually. During the non-growing season, nocturnal FCO2 exceeds daytime levels by 12.72 %, rising to 39.84 % in the algae-growing season (April to September). Piecewise structural equation models highlight gas transfer velocity as a key driver of diel FCO2 changes, with seasonal algal growth intensifying diel CO2 partial pressure variability by enhancing gross primary production, thereby amplifying diel FCO2 fluctuations. We suggest that ongoing lake eutrophication, driven by global climate change and human activities, may introduce additional uncertainties in lake CO2 emission estimates.

Transcriptome analysis and transcription factors response to transplanting and topping time of upper leaf in tobacco (Nicotiana tabacum L.)

Tobacco, as an annual industrial crop, is significantly affected by agronomic practices such as transplanting and topping, which can influence the yield and quality of the upper leaves. However, the processes by which transcription factors integrate both agronomic practices remain unclear. In this study, eight treatments were designed based on varying transplanting and topping periods. RNA-seq was employed to analyze the transcriptional expression and identify key differentially expressed genes (DEGs) and transcription factors (TFs). Subsequently, a rigorous quality inspection and data cleaning process yielded 1,302,152,358 high-quality reads. The comparative analysis of 8 treatments identified a total of 4265 DEGs. Utilizing K-means analysis, these DEGs demonstrated 9 distinct expression patterns. GO and KEGG annotation revealed a significant association of these DEGs with photosynthesis and secondary metabolism. 10 hub genes including AFC2, SIGB, PGSIP8, BIG5, OSP1, RL13, PDC1, NtORF and EBG were identified through WGCNA analysis. 41 differentially expressed TFs were identified through transcription factor analysis. Among them, 10 TFs namely ABR1, ERF26, HAT5, HSF24, LUH, AGL8, TIFY5A, TIFY10A, WRKY4, and WRKY40 are directly associated with plant stress resistance. 5 TFs such as ERF110, IDD7, ATB40, NAC81, and NAC83 have been identified as positive regulators of growth and development, while 3 TFs such as BH130, TCP4, and WRKY53 have been found to negatively impact growth and development. Furthermore, 4 TFs have been implicated in hormone and light signaling pathways, namely CIGR1, BLH1, WRKY42, and EIN4. The identified hub genes and TFs suggest that early transplanting and topping (B1D1C) contribute to enhanced stress resistance in tobacco. This may result in more developed stomata on tobacco leaves, as well as an increase in leaf thickness and a reduction in leaf size.

Visual Analytics for Machine Learning: A Data Perspective Survey.

The past decade has witnessed a plethora of works that leverage the power of visualization (VIS) to interpret machine learning (ML) models. The corresponding research topic, VIS4ML, keeps growing at a fast pace. To better organize the enormous works and shed light on the developing trend of VIS4ML, we provide a systematic review of these works through this survey. Since data quality greatly impacts the performance of ML models, our survey focuses specifically on summarizing VIS4ML works from the data perspective. First, we categorize the common data handled by ML models into five types, explain the unique features of each type, and highlight the corresponding ML models that are good at learning from them. Second, from the large number of VIS4ML works, we tease out six tasks that operate on these types of data (i.e., data-centric tasks) at different stages of the ML pipeline to understand, diagnose, and refine ML models. Lastly, by studying the distribution of 143 surveyed papers across the five data types, six data-centric tasks, and their intersections, we analyze the prospective research directions and envision future research trends.

Undoing the past to prepare for the future: Lessons learned from the data exchange project at UC Berkeley

Realigning data and integration tools after years of inconsistent management can seem overwhelming at best and impossible at worst. To meet the demands of today's tools and analytics, it is a worthwhile investment to strategically improve data quality and accessibility. Whether your institution is preparing for a customer relationship management (CRM) conversion or just trying to get a better handle on managing data, this paper will examine UC Berkeley's initiative to create business and technical solutions to increase transparency, governance and data intake while decreasing customisations and confusion for stakeholders.

Assessment of water quality and trophic state using a multipara-metric index-based approach for Lake Guineo, Lake Carraizo and Lake Cidra, Puerto Rico

To ensure a safe drinking water supply, it is necessary to protect water quality. The proposed project aims to understand water quality data analyzed from a temporal and spatial perspective on the following physiochemical parameters: DO, pH, temperature, Secchi disc turbidity, conductivity, nitrate, chlorophyll α & phosphate. The results provide information to evaluate the status of the water quality and its suitability for human consumption. These variables related to the general characteristics of water quality and trophic level were used for calculation of a water quality index (WQI) and trophic state index (TSI) to assess 3 lakes in Puerto Rico: Lake Cidra, Lake Carraizo and Lake Guineo. Presence or absence of macrophytes were monitored during six months in the three reservoirs in Puerto Rico as well as the parameters mentioned above. The objective of this investigation is to discuss the trophic state and water quality in 3 different trophic state reservoirs in Puerto Rico. Results were correlated with the density of the macrophyte species, Eichhornia crassipes. Variations of water in situ multiparametric sampling were recorded for 6 months. Thus, integrating components that define the status of reservoirs using multiparameter measurements from various perspectives; a better diagnosis is expected regarding the water quality assessment. This investigation aims to undertake a comprehensive study of water quality by implementing the WQI and TSI indices, considering physical, chemical, and biological parameters with respect to eutrophication and ecological considerations for three reservoirs in the Puerto Rico, providing information regarding the quality of water and trophic state of the chosen reservoirs. Overall WQI results revealed that the water quality improved after the Hurricane Fiona’s occurrence. Trophic State Index after the hurricane showed slight fluctuations in the reservoirs.

Machine learning in budget forecasting for corporate finance: A conceptual model for improving financial planning

This paper explores the transformative potential of machine learning (ML) in budget forecasting within corporate finance. It begins with an examination of the importance of accurate budget forecasting for financial planning and the limitations of traditional methods. Theoretical foundations of ML are then discussed, highlighting relevant techniques such as regression, time series analysis, and neural networks. A conceptual model for ML-driven budget forecasting is proposed, detailing its components, architecture, and integration into financial planning processes. The paper also addresses the expected benefits, including improved accuracy and efficiency, alongside the challenges such as data quality, ethical considerations, and organizational barriers. By navigating these challenges through robust data governance, ethical practices, and strategic implementation, organizations can significantly enhance their budget forecasting processes, leading to better financial outcomes and strategic decision-making.

Leveraging Artificial Intelligence for enhanced tax fraud detection in modern fiscal systems

The increasing sophistication of tax evasion schemes poses significant challenges to fiscal authorities worldwide, necessitating advanced technological solutions for fraud detection. This comprehensive review examines the integration of artificial intelligence (AI) technologies in modern tax administration systems, focusing on their application in detecting and preventing tax fraud. The paper analyzes various AI methodologies, including machine learning algorithms, deep learning networks, and natural language processing techniques, evaluating their effectiveness in identifying suspicious patterns and anomalies in tax-related data. Our review encompasses both theoretical frameworks and practical implementations across different jurisdictions, highlighting successful case studies and emerging challenges. The findings indicate that AI-powered systems demonstrate superior accuracy in detecting complex fraud patterns compared to traditional rule-based approaches, with some implementations showing up to 85% improvement in fraud detection rates. However, challenges persist regarding data quality, privacy concerns, and the need for continuous model adaptation to evolving fraud tactics. This review also addresses the regulatory implications and ethical considerations of implementing AI in tax administration, providing recommendations for policymakers and tax authorities to optimize their fraud detection capabilities while maintaining fairness and transparency in their operations.

Conceptual framework for data-driven reservoir characterization: Integrating machine learning in petrophysical analysis

Reservoir characterization plays a critical role in optimizing oil and gas production by accurately determining subsurface properties such as porosity, permeability, and fluid saturation. Traditionally, this process has relied on the interpretation of well logs, seismic data, and core samples using manual or physics-based methods. However, these approaches often face limitations when dealing with complex datasets and heterogeneous reservoir properties. This review develops a conceptual framework for integrating machine learning (ML) into petrophysical analysis to revolutionize reservoir characterization. By utilizing advanced ML algorithms such as supervised learning, unsupervised learning, and deep learning, this model demonstrates the potential of data-driven methods to improve the accuracy and efficiency of reservoir analysis. The framework focuses on how ML techniques can automate the interpretation of well logs, enhance seismic data processing, and predict rock properties from core samples, leading to more accurate identification of reservoir boundaries and productive zones. This approach not only reduces interpretation errors but also accelerates decision-making in reservoir management. Moreover, machine learning can handle the vast amounts of data generated in reservoir studies, enabling real-time analysis and adaptive decision support. The study also addresses challenges such as data quality, model interpretability, and computational scalability, offering insights into future applications of ML in reservoir characterization. By combining petrophysical expertise with machine learning capabilities, this framework aims to significantly advance the field of reservoir characterization and contribute to more efficient resource management in the oil and gas industry.

WEATHERING THE STORM: A SYSTEMATIC LITERATURE REVIEW OF WEATHER STATIONS’ OBSERVATIONAL PRACTICES

This literature review examines the accuracy, error frequency, and the impact of workload and decision-making on the weather observations made by PAGASA synoptic station personnel in the Cordillera Administrative Region (CAR). The accuracy of weather data collected by PAGASA is critical for reliable forecasting and timely decision-making in various sectors, including agriculture, disaster management, and transportation. The review highlights key factors influencing data accuracy, such as instrument calibration and human error. Studies show that while the accuracy of weather observations is generally high, occasional discrepancies occur, often due to technical issues or human mistakes in data recording, especially during extreme weather events. The review also explores the frequency of errors in weather observation data. Research indicates that errors are infrequent, but they are more likely to occur during severe weather conditions or in cases of equipment malfunctions or power failures. Although external factors can occasionally disrupt the data collection process, the overall frequency of errors remains relatively low. Furthermore, the impact of workload and decision-making on the accuracy of observations is discussed. Heavy workloads during peak weather seasons and the pressure of rapid decision-making during extreme weather events were found to contribute to an increased likelihood of errors. Studies emphasize the importance of managing workload and decision-making stress to maintain the quality of data. The review concludes by suggesting that further research, training, and technological improvements are needed to enhance the accuracy and reliability of weather observations in PAGASA synoptic stations in CAR.

AI for Optimizing Supply Chain Management

The rapid advancement of Artificial Intelligence (AI) technologies has significantly transformed various sectors, with supply chain management (SCM) being a notable beneficiary. This research paper explores the impact of AI on optimizing supply chain processes, focusing on its applications in predictive analytics, natural language processing, robotics and automation, blockchain, and the Internet of Things (IoT). Through a mixed-method approach involving quantitative surveys, qualitative interviews, and secondary data analysis, the study evaluates how AI-driven solutions enhance key performance indicators (KPIs) such as inventory turnover, lead time, order accuracy, and cost reduction. The results indicate substantial improvements in these KPIs post-AI implementation, highlighting AI's role in achieving greater operational efficiency, accuracy, and cost-effectiveness in SCM. Challenges associated with AI adoption, including data quality, integration with legacy systems, and skill gaps, are also discussed. The paper provides actionable insights and recommendations for organizations aiming to leverage AI technologies to optimize their supply chain operations. This research contributes to the growing body of knowledge on AI in SCM and offers practical guidance for industry practitioners

The role of big data in driving advancements in deep learning: Opportunities, challenges, and future directions

The advent of big data has significantly shaped the trajectory of machine learning, particularly in the field of deep learning. The vast amounts of data generated every day across various sectors—from healthcare to finance—have provided unprecedented opportunities for training more powerful and accurate deep learning models. This review paper explores the critical role big data plays in driving advances in deep learning, analyzing how these two fields intersect and fuel each other. The paper also examines the challenges associated with leveraging big data in deep learning, including data quality, scalability, and computational constraints. Finally, the paper discusses future directions in the convergence of big data and deep learning, emphasizing emerging trends and the potential of this intersection to revolutionize industries.