Data Analysis Tools Research Articles

Digital banking fortification: a real-time isolation forest architecture for detecting online transaction fraud

Abstract Since the use of the Internet has increased exponentially, numerous organizations, including the financial industry, offer services online. As a result, financial scams are expanding in quantity and complexity worldwide, resulting in massive revenue losses and making digital fraudulent transactions a severe issue. Abnormal attempts and illegal access are instances of these dangers that fraudulent activity detection systems must identify. Machine learning and data mining approaches have been extensively used to address this issue in recent years.
However, these approaches must be enhanced regarding real-time detection speed, tackling enormous amounts of data, and finding undiscovered attack patterns. Consequently, the present study provides a real-time architecture for averting and identifying digital transaction fraud, which relies on the Isolation Forest (IForest) approach and big data analytic tools, including Spark Streaming, sparkling water, Kafka, and PostgreSQL. This architecture seeks to improve present detection strategies by increasing accuracy for detection when considering enormous amounts of data. Two real datasets of online transactional fraud are used to assess the proposed architecture, and the findings are compared to relevant studies. The investigation results showed that IForest performed flawlessly, achieving an accuracy of 0.99 in two datasets.

Big Data Analytics: Future of Database

Abstract: Big data analytics is a revolutionary method for processing massive and complicated datasets, analysing them, and drawing important conclusions from them. Big data's introduction has caused a paradigm change in data management and analysis, giving businesses previously unheard-of opportunity to gain insightful information and make informed decisions. This study explores how big data analytics affects how well organization’s function, concentrating on the methods and tools applied across a range of sectors. We undertook an empirical analysis of case studies from businesses in the retail, healthcare, and financial sectors after conducting a thorough assessment of the literature. According to our research, using big data analytics leads to better decision-making, increased operational effectiveness, and a stronger competitive advantage. Data quality, analytics tools, and corporate culture are the main success determinants. However, issues with data privacy and the necessity for qualified data experts make the effective application of big data analytics difficult. This study adds to our understanding of big data analytics' revolutionary potential and offers useful information for practitioners and decision-makers who want to use data to their advantage.

Use of remote sensing and image processing for identification of wild orchids

A novel multi-technique approach has been applied for the identification and mapping of wild orchids using a combination of remote sensing and spectral image analysis. The five orchid species identified were the common spotted-orchid (Dactylorhiza fuchsia), heath spotted-orchid (Dactylorhiza maculata), pyramidal orchid (Anacamptis pyramidalis), heath fragrant-orchid (Gymnadenia borealis), and the dark-red helleborine (Epipactis atrorubens). Field studies have been done using a hand-held spectrometer operating in the 400–700 nm visible spectrum, photogrammetry using a digital camera as well as a multispectral image camera operating at the specific spectral bands of 450 nm (blue), 560 nm (green), 650 nm (red), 730 nm (red edge) and 840 nm (near-infrared) attached to an unmanned aerial vehicle Data analysis, using the hand-held spectrometer, followed by pattern recognition using principal component analysis and partial least squares-discriminant analysis, have identified the key distinguishing wavelengths for identification of the 5 orchid types as 400, 410, 420 and 560 nm. The use of remote sensing, using the UAV-MSI, and application of a dedicated spectral index has enabled field identification of the orchids. Finally, object-based image analysis of field gathered photogrammetry imagery, has enabled use of shape, size, and color to identify and distinguish orchid species. The developed data analytic tool, using random forest classification, can be used to identify and characterize wild orchids across multiple sites within their short lifespan with an accuracy of 86%. Any longer-term study would provide invaluable information on the diversity and complexity of orchid habitat, population variation both intra- and inter-site location, as well as the impact of climate change.

Healthcare Resource Allocation Optimization

Assuring high-quality patient care and making the best use of the resources at hand requires the efficient allocation of healthcare resources. This study uses a thorough examination of patient admission data, treatment plans, and staff availability to tackle the complex problem of optimizing healthcare resource allocation. We want to reduce wait times, optimize resource use, and eventually improve patient outcomes in healthcare facilities by integrating these essential elements. Our strategy makes use of cutting-edge data analytics tools, such as optimization algorithms and predictive modelling, to find underlying patterns and trends in patient demand, treatment regimens, and staffing needs. Our goal is to create prediction models that anticipate patient admissions, treatment requirements, and staffing levels by analysing historical data and real-time inputs. This will allow for proactive resource allocation techniques. The study's conclusions have important ramifications for healthcare administration since they provide practical advice on how to improve patient care delivery, cut wait times, and make the most use of the resources at hand. Healthcare institutions can enhance resource allocation procedures to meet the changing demands of patient care while guaranteeing the optimal use of resources by integrating technology, data-driven decision-making, and evidence-based practices. In summary, this study lays the groundwork for future investigations and innovations in hospital administration and operations while also supporting current initiatives to enhance healthcare resource allocation procedures. Healthcare organizations can improve patient outcomes and achieve operational excellence while providing high-quality, patient-centred care by adopting data-driven approaches and utilizing technology.

Presentations, management and outcomes of postoperative bariatric patients seen in the emergency department

BackgroundBariatric surgery is becoming increasingly common and postoperative patients often present to the emergency department (ED) with complications. We sought to describe the presenting complaints, management, and outcomes of postoperative bariatric surgery patients seen in the ED. MethodsWe conducted a health records review of 300 consecutive postoperative Roux-en-Y bypass surgery patients who presented to two tertiary care EDs of a major bariatric surgery center within one year of surgery. Cases were identified using a data analytic tool, and two evaluators abstracted clinical variables, imaging, treatments, and outcomes using the electronic health record. Attending emergency physicians verified the data and an experienced bariatric surgeon interpreted the computed tomography (CT) results and surgical procedures. ResultsWe included 300 patients with mean age 43.0 years, 89.7% female. Of these, 70.0% presented within 30 days of surgery and 41.7% were admitted to hospital. ED treatments included intravenous fluids (67.0%), antiemetics (53.3%), and analgesia (61.9%). Patients presenting within 30 days of surgery were more likely to undergo a CT (74.3% vs 63.3%; p = 0.06) and to have clinically important CT findings (31.9% vs 6.6%; p ≤0.001). More of the ≤30-day patients were admitted to hospital (46.2% vs 31.1%; p = 0.02). While a higher proportion of patients presenting after 30 days underwent a procedure, a large number of those were not directly related to bariatric surgery, such as appendectomy and cholecystectomy. Of the 34 patients undergoing a procedure, the majority presented with abdominal pain (76.5%). ConclusionThis is the first detailed health records review of postoperative bariatric patients seen in the ED in the emergency medicine literature. Those presenting with abdominal pain were more likely to undergo CT abdomen and a surgical procedure. Similarly, those presenting within 30 days of surgery were more likely to have significant CT findings and require hospital admission. Others presenting with primarily nausea and vomiting may improve with ED symptom management and be discharged home with bariatric team follow-up.

Estimating high-dimensional Hawkes process with time-dependent covariates

The Hawkes process models have been recently become a popular tool for modeling and analysis of neural spike train data. Despite this popularity, existing methodological and theoretical work has mainly focused on models without assumption of time-varying covariates, such as stimulus drive. In this article, motivated by neuronal spike trains study in the presence of stimuli, we propose a new Hawkes process model, where covariates are included in the intensity function. We consider the problem of simultaneous variable selection and estimation for the Hawkes process in the high-dimensional regime. Estimation of the intensity function of the high-dimensional point process is considered within a nonparametric framework, applying B-splines and the SCAD penalty for matters of sparsity. We apply the Doob-Kolmogorov inequality to establish the consistency of the resulting estimators. Finally, we illustrate the performance of our proposal through simulation and demonstrate its utility by applying it to the neuron spike train data set.

Design and Architecture of BenguetFresh: An IoT-Enabled Data-Driven System for Sustainable Agriculture

Agriculture plays a vital role in the Philippines, contributing significantly to its economy and providing livelihoods to a substantial portion of the population. Benguet province, known as the "Salad Bowl of the Philippines" for its favorable climate and fertile soil, exemplifies thriving agriculture-based livelihoods. However, challenges persist in the sector, with the low compliance rate of Philippine Good Agricultural Practices (PhilGAP) certification highlighting the need for innovative solutions to enhance sustainable practices, market access, and overall agricultural quality for Benguet farmers.
 This study presents the design and architecture of BenguetFresh a system designed to integrate data-driven monitoring and management practices with sustainable agriculture, while adhering to PhilGAP standards. Through stakeholder engagement, interviews, and systematic review, specific requirements and challenges of farmers in Benguet were identified and addressed.
 BenguetFresh employs cutting-edge technology, Arduino-based smart agriculture monitoring systems, enabling real-time data collection on environmental factors. Data analytics tools process this data to provide valuable insights, facilitating informed decision-making and resource optimization.
 The scalable architecture ensures efficient data flow and real-time processing, while user-friendly interfaces empower farmers with real-time and historical data visualization and data-driven recommendations. Furthermore, the integration of e-commerce functionality fosters direct connections between farmers and consumers, expanding market reach and improving economic outcomes.
 BenguetFresh's design and architecture serve as a blueprint for implementing data-driven, sustainable agriculture. The potential benefits extend to both farmers and consumers, ensuring high-quality, responsibly produced agricultural products. Embracing cutting-edge technology and industry standards, BenguetFresh paves the way for efficient, sustainable, and prosperous agriculture.

Sales Data Analysis Using BI and WEKA

In today's competitive business landscape, organizations rely heavily on data-driven decision-making to gain a competitive edge. Sales data analysis serves as a cornerstone in this endeavor, offering invaluable insights into consumer behavior, market trends, and the overall health of a business. This abstract highlights the significance of sales data analysis and its role in informing strategic business decisions. The abstract begins by outlining the importance of sales data analysis in understanding customer preferences, identifying emerging market trends, and optimizing sales strategies. It emphasizes the need for businesses to harness the power of data analytics tools and techniques to extract actionable insights from vast volumes of sales data. Furthermore, the abstract discusses the various dimensions of sales data analysis, including sales performance metrics, customer segmentation, and product performance analysis. It underscores the importance of leveraging advanced analytical methods such as predictive analytics, machine learning, and data visualization to unlock hidden patterns and correlations within sales data. Moreover, the abstract explores the practical applications of sales data analysis across different industries, ranging from retail and e-commerce to manufacturing and finance. It showcases real-world examples of how organizations have successfully utilized sales data analysis to enhance revenue generation, streamline operations, and improve customer satisfaction. The performance of the forecasting models is evaluated using appropriate metrics and validated against holdout datasets to ensure robustness and reliability. Model selection and tuning are conducted to optimize forecasting accuracy and mitigate potential biases. The forecasting is done using weka tool. Keywords – Insights, Visualization, Analytics, Sales trends.

State Dependent Delay Maps: Numerical Algorithms and Dynamics of Projections

This work concerns the dynamics of a certain class of delay differential equations (DDEs) which we refer to as state dependent delay maps. These maps are generated by delay differential equations where the derivative of the current state depends only on delayed variables, and not on the un-delayed state. However, we allow that the delay is itself a function of the state variable. A delay map with constant delays can be rewritten explicitly as a discrete time dynamical system on an appropriate function space, and a delay map with small state dependent terms can be viewed as a “non-autonomous” perturbation. We develop a fixed point formulation for the Cauchy problem of such perturbations, and under appropriate assumptions obtain the existence of forward iterates of the map. The proof is constructive and leads to numerical procedures which we implement for illustrative examples, including the cubic Ikeda and Mackey-Glass systems with constant and state-dependent delays. After proving a local convergence result for the method, we study more qualitative/global convergence issues using data analytic tools for time series analysis (dimension and topological measures derived from persistent homology). Using these tools we quantify the convergence of the dynamics in the finite dimensional projections to the dynamics of the infinite dimensional system.

InVADo: Interactive Visual Analysis of Molecular Docking Data.

Molecular docking is a key technique in various fields like structural biology, medicinal chemistry, and biotechnology. It is widely used for virtual screening during drug discovery, computer-assisted drug design, and protein engineering. A general molecular docking process consists of the target and ligand selection, their preparation, and the docking process itself, followed by the evaluation of the results. However, the most commonly used docking software provides no or very basic evaluation possibilities. Scripting and external molecular viewers are often used, which are not designed for an efficient analysis of docking results. Therefore, we developed InVADo, a comprehensive interactive visual analysis tool for large docking data. It consists of multiple linked 2D and 3D views. It filters and spatially clusters the data, and enriches it with post-docking analysis results of protein-ligand interactions and functional groups, to enable well-founded decision-making. In an exemplary case study, domain experts confirmed that InVADo facilitates and accelerates the analysis workflow. They rated it as a convenient, comprehensive, and feature-rich tool, especially useful for virtual screening.

Learning Aligned Vertex Convolutional Networks for Graph Classification.

Graph convolutional networks (GCNs) are powerful tools for graph structure data analysis. One main drawback arising in most existing GCN models is that of the oversmoothing problem, i.e., the vertex features abstracted from the existing graph convolution operation have previously tended to be indistinguishable if the GCN model has many convolutional layers (e.g., more than two layers). To address this problem, in this article, we propose a family of aligned vertex convolutional network (AVCN) models that focus on learning multiscale features from local-level vertices for graph classification. This is done by adopting a transitive vertex alignment algorithm to transform arbitrary-sized graphs into fixed-size grid structures. Furthermore, we define a new aligned vertex convolution operation that can effectively learn multiscale vertex characteristics by gradually aggregating local-level neighboring aligned vertices residing on the original grid structures into a new packed aligned vertex. With the new vertex convolution operation to hand, we propose two architectures for the AVCN models to extract different hierarchical multiscale vertex feature representations for graph classification. We show that the proposed models can avoid iteratively propagating redundant information between specific neighboring vertices, restricting the notorious oversmoothing problem arising in most spatial-based GCN models. Experimental evaluations on benchmark datasets demonstrate the effectiveness.

Big Data Analytic Tools Usage among Academic Libraries in Tanzania

This study examines the implementation of Big Data analytics in Tanzanian University libraries. Employing a qualitative approach within the interpretive paradigm, the study conducted interviews to collect data from 12 library staff across various University libraries in Tanzania. The qualitative data collected was analyzed using Atlasi.ti 7, focusing on emerging themes. The findings established that most University libraries in Tanzania utilize social networking sites for marketing their products and services. However, only a few academic libraries employ analytics tools such as Apache Hadoop, MongoDB, Apache Spark, Tableau, Zoho Analytics, Apache Storm, and others due to insufficient skills. The study concludes that library administrators could greatly benefit from integrating Big Data analytics into their daily operations. Recommendations include developing Big Data analytics policies to ensure proper handling of user data and offering training on the use of such analytic tools to librarians to equip them with necessary skills and techniques.

Abstract 6475: Leveraging real-world pancreatic cancer datasets to drive drug discovery and patient health

Abstract Pancreatic cancer is the third leading cause of cancer-related death in the United States. Current therapeutic options offer a dismal overall survival with the 5-year survival at just ~12%. Analysis of the clinical and molecular underpinnings of pancreatic cancer is critical to developing both early detection methodologies as well as novel therapeutic options. The aggressiveness and deadly nature of this disease warranted the development of a data repository and analysis system dedicated to pancreatic cancer data. The Pancreatic Cancer Action Network’s (PanCAN) SPARK platform is a cloud-based data and analytics platform, powered by Velsera, that integrates real-world patient health data from PanCAN research initiatives and accelerates research by making pancreatic cancer data easier to access and use. Encompassing clinical, imaging, and genomics data from over 600 patients with pancreatic cancer within PanCAN’s Know Your Tumor ® (KYT) precision medicine service, the SPARK platform connects with petabytes of publicly available cancer data via the Cancer Genomics Cloud (CGC), also powered by Velsera. The CGC is part of NCI’s Cancer Research Data Commons (CRDC), a cloud-based data science infrastructure that connects data with analytics tools to allow researchers to share, integrate, analyze, visualize, and drive scientific discovery. Here, we demonstrate the application of these datasets by providing a case study demonstrating how to combine and enrich data to accelerate pancreatic cancer research. Currently, the genomic and proteomic data available on CRDC amounts to 402 and 304 cases of pancreatic tumor samples, respectively. We will use the capabilities of the SPARK and CGC platforms, which provide ready-to-use tools for multi-omics analysis that require no coding knowledge. Using the KYT and CRDC open-access pancreatic cancer data, we aim to demonstrate how to perform integrated analysis of data from diverse scientific domains, and share with collaborators all in one space, streamlining and increasing the potential for new scientific discoveries. Further expansion of the PanCAN and CGC datasets will undoubtedly provide a more comprehensive understanding of pancreatic cancer tumor biology. SPARK and CGC’s cloud based computation infrastructure, along with numerous available cancer datasets and easy-to-use multi-omics data processing workflows and data analytic tools will be instrumental in this process. Citation Format: Kawther Abdilleh, Zelia Worman, Rowan Beck, Cera Fisher, Divya Sain, Jack DiGiovanna, Lynn Matrisian, Sudheer Doss, Brandi Davis-Dusenbery. Leveraging real-world pancreatic cancer datasets to drive drug discovery and patient health [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6475.

Monitoring the psychological component of higher education quality using ICT tools

This study examines the use of information and communication technologies (ICT) to monitor the psychological component of higher education quality. A literature review covers the concepts of higher education quality and its monitoring, the psychological factors involved, and the potential of ICT tools, including Google services. The study details a monitoring procedure using Google Forms to assess indicators like relationships between participants, satisfaction levels, and organisational climate. The computer program “Personnel – Ψ” is also presented as a tool for comprehensive psychological diagnostics of teachers. The advantages of using ICT tools for efficient data collection, analysis and management are discussed. The results demonstrate the feasibility and effectiveness of using ICT to improve monitoring of the psychological aspects of educational quality and make evidence-based decisions to enhance the educational environment. The use of user-friendly tools like Google Forms facilitates regular assessment of quality indicators and aids institutions in ensuring participant satisfaction and optimal conditions for learning and growth.

Integrated Service Architecture to Promote the Circular Economy in Agriculture 4.0

Innovation has been the transforming tool of precision agriculture as a response to population growth and the demand for more food with quality, less waste, food security, and sustainable management of environmental resources. The challenges are to increase the productivity of cultivated areas, both for current and future areas, to manage the use of potable water, scarce in many regions, to keep the soil fertile, and to reduce waste through reuse, optimization, resource sharing, and operational and strategic management based on accurate information of planting, harvesting, and management of environmental conditions, which are also objectives of the Circular Economy. Therefore, using Industry 4.0 technologies in agriculture becomes fundamental to facing such challenges. This paper presents a systematic literature review on Industry 4.0 technologies adopted in agriculture for sustainable development, considering environmental, economic, and social benefits. The research pointed to the use of IoT in irrigation control systems by sending automatic commands, monitoring soil and weather conditions, in the use of machinery with some automation features and in cloud data storage systems, and with the use of Big Data analytical tools, with access by mobile devices, these uses contribute to operational and strategic decision making in the management of planting and harvesting. However, the literature review did not find a technological architecture for Integrated Services in Agriculture 4.0. Thus, this paper proposes a Service Architecture that enables the promotion of a Circular Economy in Agriculture 4.0. The contribution of this article to the theory is in the expansion of knowledge of the use of technologies in Agriculture 4.0. In terms of practice, this article provides an Integrated Service Architecture so that new products can be developed for Agriculture 4.0 and thus contribute to society in reducing food insecurity, generating environmental, economic, and social benefits, and promoting the Circular Economy in Agriculture 4.0.

Assessment of Determinant Sources of Plastics and Microplastics Pollution in Inland Waterways Navigation in Lower River Niger

This study was aimed at assessing the impact of plastics and micro plastics pollution in Nigerian inland waterways operations. The main aim of this study is to provide a baseline assessment of plastic pollution in the River Niger, along with recommendations for further research. Using a survey and appropriate data analysis tools, the study investigated the determinant sources of plastic pollution in the River Niger, as well as the most significant impact and preferred means of plastic pollution and regulation. The main findings indicate that disposal of plastics is the determinant source of plastics and micro plastics in the River Niger. The most significant impact of plastic pollution was identified as reduction in the accessibility of certain areas of the river. Behavioral instrument is indicated to be the most preferred means of plastic pollution control and regulation. Hence, there is an urgent need for improved awareness among local communities. This can be achieved through education programs, which will help to reduce the use of single-use plastics while also reducing littering in these areas. The paper also recommends that more research be conducted on how these pollutants affect human health and ecosystems.

Behavioral intentions in embracing cloud-based accounting information systems

In facing the digital era and a more competitive environment, every organization is required to increasingly implement information systems that can facilitate various organizational needs. Cloud Based Accounting Information Systems (CBAIS), as part of information systems (IS), have also gained attention of organizations. This research was conducted to obtain empirical evidence of the interest in using CBAIS in various medium-sized companies in Indonesia measured using Institutional Theory. The data analysis tool used was SEM- PLS. The respondents in this study were accounting and finance departments employees working for logistics companies that still use conventional accounting information systems (non-cloud-based). A total of 89 responses were collected from 5 logistics companies in Indonesia. The research results indicated that mimetic pressure positively influenced the interest in using CBAIS, coercive pressure does not positively influence the interest in using CBAIS, and normative pressure positively influenced the interest in using CBAIS. An interesting aspect of this study is the absence of regulation or even demand in Indonesia that obligates the use of CBAIS. Hence, the use of CBAIS has not become a commonly adopted best practice in logistics companies.

Emerging Data Processing Methods for Single‐Entity Electrochemistry

AbstractSingle‐entity electrochemistry is a powerful tool that enables the study of electrochemical processes at interfaces and provides insights into the intrinsic chemical and structural heterogeneities of individual entities. Signal processing is a critical aspect of single‐entity electrochemical measurements and can be used for data recognition, classification, and interpretation. In this review, we summarize the recent five‐year advances in signal processing techniques for single‐entity electrochemistry and highlight their importance in obtaining high‐quality data and extracting effective features from electrochemical signals, which are generally applicable in single‐entity electrochemistry. Moreover, we shed light on electrochemical noise analysis to obtain single‐molecule frequency fingerprint spectra that can provide rich information about the ion networks at the interface. By incorporating advanced data analysis tools and artificial intelligence algorithms, single‐entity electrochemical measurements would revolutionize the field of single‐entity analysis, leading to new fundamental discoveries.

Emerging Data Processing Methods for Single-Entity Electrochemistry.

Single-entity electrochemistry is a powerful tool that enables the study of electrochemical processes at interfaces and provides insights into the intrinsic chemical and structural heterogeneities of individual entities. Signal processing is a critical aspect of single-entity electrochemical measurements and can be used for data recognition, classification, and interpretation. In this review, we summarize the recent five-year advances in signal processing techniques for single-entity electrochemistry and highlight their importance in obtaining high-quality data and extracting effective features from electrochemical signals, which are generally applicable in single-entity electrochemistry. Moreover, we shed light on electrochemical noise analysis to obtain single-molecule frequency fingerprint spectra that can provide rich information about the ion networks at the interface. By incorporating advanced data analysis tools and artificial intelligence algorithms, single-entity electrochemical measurements would revolutionize the field of single-entity analysis, leading to new fundamental discoveries.

A Novel Approach for Mixed-Methods Research Using Large Language Models: A Report Using Patients' Perspectives on Barriers to Arthroplasty.

Mixed-methods research is valuable in health care to gain insights into patient perceptions. However, analyzing textual data from interviews can be time-consuming and require multiple analysts for investigator triangulation. This study aims to explore a novel approach to investigator triangulation in mixed-methods research by employing a large language model (LLM) for analyzing data from patient interviews. This study compared the thematic analysis and survey generation performed by human investigators and ChatGPT-4, which uses GPT-4 as its backbone model, using data from an existing study that explored patient perceptions of barriers to arthroplasty. The human- and ChatGPT-4-generated themes and surveys were compared and evaluated based on their representation of salient themes from a predetermined topic guide. ChatGPT-4 generated analogous dominant themes and a comprehensive corresponding survey as the human investigators but in significantly less time. The survey questions generated by ChatGPT-4 were less precise than those developed by human investigators. The mixed-methods flowchart proposes integrating LLMs and human investigators as a supplementary tool for the preliminary thematic analysis of qualitative data and survey generation. By utilizing a combination of LLMs and human investigators through investigator triangulation, researchers may be able to conduct more efficient mixed-methods research to better understand patient perspectives. Ethical and qualitative implications of using LLMs should be considered.