Customer Characteristics Research Articles

Research on Credit Card Fraud Risk Identification Based on Integrated Logistic Regression Model

Effectively identifying credit card fraud using machine learning methods is a significant issue in the financial sector. In this context, machine learning models encounter challenges such as the imbalanced distribution of sample data labels and the high dimensionality of customer feature sets. Addressing these two critical factors, this paper develops an enhanced method for the logistic regression model. This approach not only balances the sample label distribution through resampling but also mitigates the estimation issues arising from the curse of dimensionality. Furthermore, the proposed method addresses the coverage issue of the entire feature set. It solves that resampling can only partially address the curse of dimensionality problem and employs L1 regularization for each logistic regression submodel to further alleviate this issue. Results from simulation experiments and real-world data analysis demonstrate that the proposed method is competitive with logistic regression and several classical classification techniques. This method is not only effective in resolving credit card fraud risks but also has the potential to be extended to other domains.

Ring: A Lightweight and Versatile Cross-Platform Dynamic Programming Language Developed Using Visual Programming

New programming languages are often designed to keep up with technological advancements and project requirements while also learning from previous attempts and introducing more powerful expression mechanisms. However, most existing dynamic programming languages rely on English keywords and lack features that facilitate easy translation of language syntax. Additionally, maintaining multiple implementations of the same language for different platforms, such as desktops and microcontrollers, can lead to inconsistencies and fragmented features. Furthermore, they usually do not use visual programming to fully implement the compiler and virtual machine. In this research paper, we introduce Ring—a dynamically-typed language with a lightweight implementation. However, it boasts several advantages, including a rich and versatile standard library and direct support for classes and object-oriented programming. The Ring language offers customization features. For instance, it allows easy modification of the language syntax multiple times, enabling programming by writing code using Arabic, English, or other keywords. Additionally, the language permits the creation of domain-specific languages through new features that extend object-oriented programming, allowing for specialized languages resembling CSS or Supernova. In the era of the Internet of Things, instead of creating another language implementation to support microcontrollers, the same Ring implementation allows us to create projects and applications for desktops, the web, WebAssembly, Android, or Raspberry Pi Pico. The Ring Compiler and Virtual Machine are designed using the PWCT Visual Programming language based on ANSI C. The visual implementation is composed of 18,945 components that generate 24,743 lines of code, which increases the abstraction level by approximately 23.5% and hides unnecessary details.

Creating a Quasi-Resonant Induction Cooktop Integrating Zero-Voltage Switching (ZVS) and Load Management

This study aims to elucidate the development and construction of a durable induction cooktop, with key considerations including efficiency, power customization, and safety features. The intricate processes involved in crafting a 3.5 kW induction burner are thoroughly examined, encompassing simulations for quasi-resonant inverters, the meticulous selection of induction coils and capacitors, the implementation of practical Analog-to-Digital Converter (ADC) filtration, pulse width modulation (PWM) driving techniques, and the integration of protection mechanisms. Leveraging an ARM-based microcontroller enabled the attainment of diverse objectives such as Zero-Voltage Switching (ZVS), safeguarding IGBTs, facilitating user interaction through a user-friendly interface, and enabling load detection capabilities. Furthermore, the capability to gauge and adjust output power based on user preferences was incorporated. Subsequently, rigorous testing was conducted to evaluate the functionality and applicability of the device in real-world scenarios.

Elevating Vocational Training: The Power of Learning Management Systems in Shaping Digital Skills

This article examines the impact of Learning Management Systems (LMS) on the development of learners' technological skills within the context of vocational training. Drawing on an analysis of pedagogical practices and recent studies, it explores how the use of LMS facilitates the acquisition of digital skills essential for the employability of future professionals. The article highlights the advantages of LMS in terms of personalized learning paths, flexible access to content, and tracking of learners' progress. It also discusses the challenges associated with the adoption of LMS, particularly in terms of faculty training and technological integration. The findings of this study emphasize that LMS are not just content management tools, but they play a central role in preparing learners to meet the technological requirements of the current job market. The customization features of LMS allow learners to engage with content in a way that suits their individual learning styles and pace. This personalized approach can lead to more effective skill development and a deeper understanding of technological concepts. Furthermore, the flexibility offered by LMS in accessing learning materials enables learners to engage with the content at their convenience, which is particularly beneficial for individuals balancing work and study commitments. Additionally, the ability to track learners' progress through LMS provides valuable insights for educators to tailor their teaching methods and interventions to address specific areas of need. However, the adoption of LMS also presents challenges, particularly in ensuring that educators are proficient in utilizing the technology to its full potential. Effective training and support for faculty members are crucial in maximizing the benefits of LMS for skill development. Furthermore, integrating LMS into existing educational systems requires careful planning and consideration to ensure seamless implementation and usability. In conclusion, this article underscores the significant role of LMS in fostering the technological skills of learners in vocational training. By leveraging the capabilities of LMS, educational institutions can better prepare their students for the demands of the contemporary workforce, ultimately enhancing their employability and competitiveness in the job market.

Understanding public opinion and discussion dynamics of digital humans on social media: an analysis of sentiment, themes and user characteristics

PurposeThe emergence of artificial intelligence-generated content (AIGC) technology has markedly enhanced the capabilities of digital human content generation and natural language processing, thus further advancing the development of digital humans. To enable enterprises and governments to effectively address the challenges and opportunities arising from the rapid development of digital humans, it is imperative to understand the public opinion and discussion dynamics of digital humans.Design/methodology/approachThis study initially analyzed the trends and distribution patterns of public attention to digital humans. By utilizing word cloud technology, we explored the primary focal points of public interest and conducted a topic analysis using latent Dirichlet allocation (LDA) techniques. Subsequently, content analysis was conducted on the popular application domains of digital humans. Finally, this study examined the influence of user characteristics on emotional scores toward digital humans and the presence of differences in focus across user groups.FindingsThe results indicate a sustained increase in public attention toward digital humans, accompanied by notable geographic disparities in the distribution of discussions. Discussions on Weibo are primarily focused on four domains, whereas areas within the digital human application domain that provoke widespread discussion include live streaming, service, cultural entertainment and digital avatars. Significant impacts of user characteristics on sentiment scores were observed, revealing divergent focal points of interest among different user groups toward digital humans.Originality/valueThrough the deep analysis of Weibo data, this study offers new insights into the digital human industry, enabling governments and businesses to understand industry trends and develop targeted digital human customization strategies based on customer characteristics.

The use of TruCare III insulin pump in patients with type 1 diabetes mellitus

The development of devices for continuous subcutaneous insulin infusion (CSII or insulin pumps) dramatically improved medical care for patients with diabetes mellitus. Insulin pump production widens annually resulting in number of new models entering the market, that differs in price but are similar in technical features. The entering of such new models to the Russian market can cause practical issues both in patient and in health care provider, so their estimation is of great importance. Insulin pump TruCare III (Apex Medical Co., Ltd, China) was registered in Russian Federation in September 15, 2023. The clinical experience of the TruCare III use in patients with type 1 diabetes mellitus is presented with the focus on glycemic parameters and custom features.

Improving Pelvic Floor Muscle Training with AI: A Novel Quality Assessment System for Pelvic Floor Dysfunction.

The first line of treatment for urinary incontinence is pelvic floor muscle (PFM) training, aimed at reducing leakage episodes by strengthening these muscles. However, many women struggle with performing correct PFM contractions or have misconceptions about their contractions. To address this issue, we present a novel PFM contraction quality assessment system. This system combines a PFM contraction detector with a maximal PFM contraction performance classifier. The contraction detector first identifies whether or not a PFM contraction was performed. Then, the contraction classifier autonomously quantifies the quality of maximal PFM contractions across different features, which are also combined into an overall rating. Both algorithms are based on artificial intelligence (AI) methods. The detector relies on a convolutional neural network, while the contraction classifier uses a custom feature extractor followed by a random forest classifier to predict the strength rating based on the modified Oxford scale. The AI algorithms were trained and tested using datasets measured by vaginal dynamometry, combined in some cases with digital assessment results from expert physiotherapists. The contraction detector was trained on one dataset and then tested on two datasets measured with different dynamometers, achieving 97% accuracy on the first dataset and 100% accuracy on the second. For the contraction performance classifier, the results demonstrate that important clinical features can be extracted automatically with an acceptable error. Furthermore, the contraction classifier is able to predict the strength rating within a ±1 scale point with 97% accuracy. These results demonstrate the system's potential to enhance PFM training and rehabilitation by enabling women to monitor and improve their PFM contractions autonomously.

Explainable artificial intelligence to improve the resilience of perishable product supply chains by leveraging customer characteristics

AbstractOptimizing costs and profits while meeting customer demand is a critical challenge in the development of perishable supply chains. Customer-centric demand forecasting addresses this challenge by considering customer characteristics when determining inventory levels. This study proposes a solution framework comprising two steps: (a) segmentation using customer characteristics and (b) demand forecasting for each segment using transparent and responsible artificial intelligence techniques. We employed k-means, hierarchical clustering, and explainable AI (XAI) to segment, model, and compare several machine-learning techniques for demand forecasting. The results showed that support vector regression outperformed the autoregressive models. The results also showed that the two-step segmentation and demand forecasting process using hierarchical clustering and LSTM outperforms (Weighted average RMSE across segments = 61.57) the conventional single-step unsegmented forecasting process (RMSE overall data = 238.18). The main implication of this study is the demonstration of XAI in enhancing transparency in machine learning and an improved method for reducing forecasting errors in practice, which can strengthen the supply chain resilience for perishable products.

An approach of designing a child-height-assisted robot with semi-autonomous enhances social reciprocity for children with autism spectrum disorders

Individuals with autism spectrum disorder (ASD) often face significant challenges in social reciprocity, which involves the mutual exchange of social cues and interactions. This study investigates the potential of using a child-height assistive robot named Rudolf to enhance the social reciprocity skills of children with ASD. The research focused on two main questions: how the robot’s semi-autonomous functions influence the enhancement of social reciprocity and how its customizable features elicit and improve these skills. Rudolf was specifically designed to engage children with ASD in a structured, supportive environment, offering tailored interactions to practice social reciprocity. A multiple-probe design was employed over three months to evaluate the robot’s impact on the social skills of three participants with ASD. The study revealed significant improvements in the children’s social reciprocity, with participants demonstrating increased engagement, trust, and interaction within the robot-assisted environment. The customizable functionalities of Rudolf were particularly effective in eliciting and reinforcing interactive behaviors. This research highlights the potential of assistive robots, like Rudolf, in addressing the unique social challenges faced by individuals with ASD. The findings suggest that such robots, when designed with customizable, child-centered features, can significantly enhance social skills in this population. The study contributes to the development of tailored assistive technologies that improve social integration and overall quality of life for children with ASD.

Bringing Calm to Antibiotic Stewardship: Customizing and Automating Antibiogram Creation at a Multi-Hospital Institution

Abstract We sought to automate antibiogram creation at our multi-hospital institution with custom features including transparency into data filtering, expanding the granularity to include multi-resistant organisms, and additional conditional formatting based on sensitivity percentages. We automated creation of the antibiogram using a python framework with embedded SQL scripts. The sensitivity data for isolates from the prior year was retrieved from our lab information system. It was filtered to include only inpatient, emergency department, and observation patients across all seven hospitals in our system. Additionally, the data was filtered to only include the first organism per patient per year. Finally, organisms meeting specific sensitivity criteria (i.e. methicillin resistant Staphylococcus aureus) were included as separate rows beneath the parent organism. This data was inserted into an excel workbook with customized formatting to include the institutional logo, coloring based on sensitivity percentages, and customizable comments. Each of these steps are easily editable year-to-year to allow for changing requirements. At each step of filtering, the integrity of the data was extensively validated to make sure it was performing as intended. The antibiograms are generated within a few minutes in a fully automated manner (Figure 1). These will be distributed systemwide after review by the Medical Microbiology directors and Antimicrobial Stewardship Committee in January of each year. The code was made in an easily editable, modular way such that requests for additional separation of organisms by sensitivity, removing drugs not pertinent to our formulary, and editing what organisms appear is easily managed by the informatics team on a year-to-year basis.

ELEMENTS OF RETAIL STORE INTERIOR DESIGN : A QUALITATIVE STUDY ON ENHANCING CUSTOMER IN STORE EXPERIENCE

This research aimed to formulate the essential elements in retail store interior design. The retail store landscape is expected to undergo significant changes and trends in 2024. In this context, digitalization is expected to grow directly in proportion to e-commerce. Several AI-related concepts are also becoming increasingly favored. There are opportunities to explore key design elements in adapting to these developments. A good understanding of these elements can enhance the store’s image and create a positive experience. A qualitative method was also used to obtain 10 participants through focus group discussions involving retail store visitors as well as experts and interior product designers. The results showed that there are several important elements in designing retail store interiors, including physical elements such as the exterior area, interior area, display area, interior layout, and point of purchase. These physical elements play a significant role in creating an attractive and functional store appearance. Additionally, social elements are also important, including merchant characteristics, merchant outfits, crowding, customer characteristics, and privacy. These elements help in creating symbols and meanings relevant to visitors. Therefore, retail interior design that considers the store exterior, store interior, interior layout, and store displays can create a pleasant and meaningful shopping experience for customers

A Bag-of-Words Approach for Information Extraction from Electricity Invoices

In the context of digitization and automation, extracting relevant information from business documents remains a significant challenge. It is typical to rely on machine-learning techniques to automate the process, reduce manual labor, and minimize errors. This work introduces a new model for extracting key values from electricity invoices, including customer data, bill breakdown, electricity consumption, or marketer data. We evaluate several machine learning techniques, such as Naive Bayes, Logistic Regression, Random Forests, or Support Vector Machines. Our approach relies on a bag-of-words strategy and custom-designed features tailored for electricity data. We validate our method on the IDSEM dataset, which includes 75,000 electricity invoices with eighty-six fields. The model converts PDF invoices into text and processes each word separately using a context of eleven words. The results of our experiments indicate that Support Vector Machines and Random Forests perform exceptionally well in capturing numerous values with high precision. The study also explores the advantages of our custom features and evaluates the performance of unseen documents. The precision obtained with Support Vector Machines is 91.86% on average, peaking at 98.47% for one document template. These results demonstrate the effectiveness of our method in accurately extracting key values from invoices.

Ultrasonic-Assisted Conversion of Micrometer-Sized BiI3 into BiOI Nanoflakes for Photocatalytic Applications

This work describes a novel method for converting bismuth triiodide (BiI3) microplates into bismuth oxyiodide (BiOI) nanoflakes under ultrasonic irradiation. To produce BiOI nanoflakes with a high yield and high purity, the conversion process was carefully adjusted. Rapid reaction kinetics and increased mass transfer are benefits of the ultrasonic-assisted approach that result in well-defined converted BiOI nanostructures with superior characteristics. The produced BiOI nanoflakes were examined utilizing a range of analytical methods, such as Transmission Electron Microscopy (TEM), scanning electron microscopy (SEM) and X-ray diffraction (XRD). The progress in the ultrasonic conversion process with time was monitored through diffuse reflectance spectroscopy (DRS). The outcomes demonstrated the effective conversion of BiI3 microplates into crystalline, homogeneous, high-surface-area BiOI nanoflakes. Additionally, the degradation of organic dyes (methylene blue) under ultraviolet (UV) light irradiation was used to assess the photocatalytic efficacy of the produced BiOI nanoflakes. Because of their distinct morphology and electrical structure, the BiOI nanoflakes remarkably demonstrated remarkable photocatalytic activity, outperforming traditional photocatalysts. The ability of BiOI nanoflakes to effectively separate and utilize visible light photons makes them a viable option for environmental remediation applications. This work not only shows the promise of BiOI nanoflakes for sustainable photocatalytic applications but also demonstrates a simple and scalable approach to their manufacturing. The knowledge gathered from this work opens up new avenues for investigating ultrasonic-assisted techniques for creating sophisticated nanomaterials with customized characteristics for a range of technological uses.

Alquist 5.0: Dialogue Trees Meet Generative Models, a Novel Approach for Enhancing SocialBot Conversations

This article introduces Alquist 5.0, our SocialBot that was designed for the Alexa Prize SocialBot Grand Challenge 5. Building upon previous iterations, we present the integration of our novel neural response generator (NRG) Barista within a hybrid architecture that combines traditional predefined dialogues with advanced neural response generation. We provide a comprehensive analysis of the current state-of-the-art NRGs and large language models (LLMs), leveraging these insights to enhance Barista’s capabilities. A key focus of our development was in ensuring the safety of our chatbot and implementing robust measures to prevent profanity and inappropriate content. Additionally, we incorporated a new search engine to improve information retrieval and response accuracy. Expanding the capabilities of our system, we designed Alquist 5.0 to accommodate multimodal devices, utilizing APL templates enriched with custom features to deliver an outstanding conversational experience complemented by an excellent user interface. This paper offers detailed insights into the development of Alquist 5.0, which effectively addresses evolving user demands while preserving its empathetic and knowledgeable conversational prowess across a wide range of topics.

Analysis of Member Quality and Portfolio Quality in Deposit-Taking SACCOs in Kenya: Positivism Paradigm Approach

Deposit-Taking SACCOs have been actively recruiting and expanding financial services to promote financial inclusion, reaching out to all segments of society, especially the underserved populations, particularly those marginalized in rural areas. However, during membership recruitment, traits such as loyalty, profitability, engagement, and advocacy set high-quality members apart. These traits play pivotal roles in driving business growth, building brand reputation, and ensuring long-term sustainability. During the loan appraisal and approval process, customer characteristics and their perceived value carry significant weight. Therefore, evaluating member quality in terms of creditworthiness, financial literacy, and the ability to make timely payments stands as the central activity in the loan appraisal and approval process. Nevertheless, the empirical studies that were reviewed have presented diverse findings on this subject. The present study, therefore, investigated the effect of member quality on portfolio quality in deposit-taking SACCOs in Kenya. The study used primary data, and structured and unstructured questionnaires were administered to purposely selected credit managers in deposit-taking SACCOs in Kenya. Results of the study revealed that member quality positively and significantly influences the portfolio quality of DT SACCOs in Kenya (p =0.000<0.05) and R2= 31.9%. These results are essential to SACCO managers, SACCO regulators like SASRA, scholars, and policymakers like the government.

Addressing the Complex Needs of Customers Who Contact the Veterans Crisis Line.

Since its creation in 2007, the Veterans Crisis Line (VCL) has provided 24/7, confidential crisis support services for Veterans, Service Members, and their families, supporting the VA's highest clinical priority of suicide prevention. As part of this effort, VCL created the Customers with Complex Needs (CWCN) program to manage the individual needs and operational impact of VCL customers who call at a high frequency, are abusive toward hotline staff, exhibit sexually inappropriate behavior, and/or make threats of violence. This paper describes the VCL CWCN program and customer characteristics. Call data from 2012 to 2022, including operational data for 1,096 CWCN customers identified from October 2017 to December 2020, were used for analysis. At the cohort's peak size in 2020, calls from CWCN customers accounted for 0.4% of all distinct phone numbers received by VCL and for 22.1% of total VCL call volume. Implementation of the CWCN program was associated with significant annual reductions in average individual call volume among high frequency callers. However, no change in call volume was observed among nonhigh frequency callers. Formative challenges and future directions for the CWCN program and implications for other crisis lines are discussed.

Data-Driven Clustering and Feature-Based Retail Electricity Pricing with Smart Meters

The adoption of smart meters and dynamic pricing programs is rapidly increasing among electric utility companies. In “Data-Driven Clustering and Feature-Based Retail Electricity Pricing with Smart Meters,” Keskin, Li, and Sunar analyze how utility companies should use smart meter data for better pricing decisions. Utility companies typically have access to consumption patterns and high-dimensional features on customer characteristics and exogenous factors. The authors identify that such feature data can exhibit different forms of heterogeneity—over time and over customers. They show that the different forms of feature heterogeneity significantly worsen the best profit performance that can be achieved by a data-driven dynamic pricing policy. The authors also develop a policy based on joint spectral clustering and contextual dynamic pricing and prove that this policy achieves near-optimal profit performance.

ConvNext Mixer‐Based Encoder Decoder Method for Nuclei Segmentation in Histopathology Images

ABSTRACTHistopathology, vital in diagnosing medical conditions, especially in cancer research, relies on analyzing histopathology images (HIs). Nuclei segmentation, a key task, involves precisely identifying cell nuclei boundaries. Manual segmentation by pathologists is time‐consuming, prompting the need for robust automated methods. Challenges in segmentation arise from HI complexities, necessitating advanced techniques. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNNs), have transformed nuclei segmentation. This study emphasizes feature extraction, introducing the ConvNext Mixer‐based Encoder‐Decoder (CNM‐ED) model. Unlike traditional CNN based models, the proposed CNM‐ED model enables the extraction of spatial and long context features to address the inherent complexities of histopathology images. This method leverages a multi‐path strategy using a traditional CNN architecture as well as different paths focused on obtaining customized long context features using the ConvNext Mixer block structure that combines ConvMixer and ConvNext blocks. The fusion of these diverse features in the final segmentation output enables improved accuracy and performance, surpassing existing state‐of‐the‐art segmentation models. Moreover, our multi‐level feature extraction strategy is more effective than models using self‐attention mechanisms such as SwinUnet and TransUnet, which have been frequently used in recent years. Experimental studies were conducted using five different datasets (TNBC, MoNuSeg, CoNSeP, CPM17, and CryoNuSeg) to analyze the performance of the proposed CNM‐ED model. Comparisons were made with various CNN based models in the literature using evaluation metrics such as accuracy, AJI, macro F1 score, macro intersection over union, macro precision, and macro recall. It was observed that the proposed CNM‐ED model achieved highly successful results across all metrics. Through comparisons with state‐art‐of models from the literature, the proposed CNM‐ED model stands out as a promising advancement in nuclei segmentation, addressing the intricacies of histopathological images. The model demonstrates enhanced diagnostic capabilities and holds the potential for significant progress in medical research.

Microwaves induced epitaxial growth of urchin like MIL-53(Al) crystals on ceramic supports

Shaping Metal–Organic Frameworks (MOFs) poses a significant challenge for their widespread application on a large scale. In particular, a precise control over crystal orientation and arrangement on substrates are expected to provide exiting opportunities for novel materials with customized characteristics and enhanced performance in catalysis, gas storage, sensing, optics and electronics. Here we demonstrated for the first time that microwave irradiation can induce well controlled epitaxial growth of urchin-like MIL-53(Al) crystals via the hydrothermal conversion of Atomic Layer Deposition alumina layers on SiC foams. The resulting large, ordered crystals feature specific size, homogeneity, dispersion, and quantity that strongly correlate with the nature of the ceramic support and its ability to absorb microwaves. Furthermore, the supported MIL-53(Al) urchins were considered as templates for generating nanostructured alumina fibers on SiC foams, providing attractive catalyst carriers with high specific surface areas.

Retraction Note: IoT-based intrusion detection system for healthcare using RNNBiLSTM deep learning strategy with custom features

Retraction Note: IoT-based intrusion detection system for healthcare using RNNBiLSTM deep learning strategy with custom features