Technical Background Research Articles

Erőszakos radikalizmus kockázatbecslése – elméleti háttér és kutatási eredmények

Összefoglalás. A tanulmány a terrorveszély felismerésének és kezelésének elméleti és technikai összefoglalását nyújtja. Kiemelten foglalkozik a kockázatbecslés technikájával, és bemutat egy új, mesterséges intelligencián alapuló eljárást, amelynek segítségével 90%-os sikereséllyel lehet azonosítani azokat, akik terrortámadásokat hajthatnak végre. E mellett, az eljárás által szolgáltatott adatok felhasználásával sikerült leírni a radikálisok két típusát, amelyeket megközelítőleg az „alárendelt/erőszakos” és a „vezető/nem-erőszakos” szavakkal jellemezhetnénk. A két csoport között jelentős különbségek voltak a családi háttér, iskolázottság, radikalizálódási folyamat, állampolgársági múlt, bűnözői előélet, és szerepvállalási jellegzetességek tekintetében. Summary. Although Hungary is in a privileged position regarding the threat of terrorism, the history of other countries suggests that similar good positions can be temporary. The threat of terrorism can be investigated by several scientific approaches. After reviewing these, we analyze the theoretical and technical background of risk assessment, and present the results of our recently concluded research. In this we examined the US database PIRUS, which contained 112 types of personal data of 2,148 radicals. About half of them did carry out terrorist attacks the other half did not. Based on the individual characteristics of the radicals, the XGBoost machine learning algorithm correctly identified the perpetrators of the terrorist attacks with a probability of 87%. By using the data provided by the software, it was also possible to describe two types of radicals, which could be roughly characterized by the words “subordinate/violent” and “leader/non-violent”. The former usually had a criminal but not a radical background. They converted late in life (if their radicalization was of a religious nature) and adopted radical ideas as adults (if their radicalization was nonreligious in nature). They played a subordinate role in terrorist groups, required training and were largely influenced by social media. They also belonged to low social classes and had many personal problems. In contrast, non-violent extremists were characterized by a family tradition of radicalism, mostly had no criminal past, belonged to higher social strata, and played leading roles in terrorist organizations. Instead of committing attacks, they engaged in illegal activity by supporting terrorist organizations. The two main types probably consist of subtypes. Compared to violent extremists who were radicalized in prison, for example, those who were not radicalized in prison were mostly foreigners, were often unemployed despite their higher education, and compared to those radicalized in prison, they committed lesser crimes before radicalization. Similar subgroups occurred in both main groups, but their detailed characterization requires further research. Our findings suggest that artificial intelligence can become a good tool for the risk assessment of radicals concerning their proneness to perform terrorist attacks. Moreover, the risk assessment tool employed here may be useful in typifying radicals, and studying their radicalization routes.

Standard development for Eddy Current Arrays in lieu of Magnetic Particle Testing

The technology of Eddy Current Arrays has advanced considerably in recent years. In several trials, superior performance compared to magnetic particle testing was shown. In response, ASME has published new articles on Eddy Current Array (ECA) testing in the 2019 edition of the BPV, and IIW has started a working group to develop ISO standards for the use of eddy current array testing in lieu of magnetic particle testing. Significant interest has been indicated by stake holders, including manufacturers, end-users and regulators. In the paper, the work performed in the IIW working group will be presented. This includes a literature survey on the relative performance of eddy current array testing and magnetic particle testing. In particular, the performance in terms of probability of detection and characterization will be explored. The technical background of performance differences with conventional eddy current testing, magnetic particle testing and dye penetrant testing will be evaluated. Conclusions are drawn on the most important properties to be treated in a new ISO standard in the ISO 17635 framework. The scope of the IIW working group includes a general standard, a weld testing standard and acceptance criteria. Finally, the issues discussed in standard development will be presented and the resulting formulations explained. Comparisons will be made between the ASME and IIW/ISO resolutions.

Painting with Data: Visually based open-source tool for geo-computing

In this article we present, the conceptual and technical background of a tool for mapping and geo-computing, Painting with Data (PWD). PWD was inspired by early computer mapping algorithms that focused on drawing as an intuitive interface between spatial data and architectural practice. PWD embraces the potential of such techniques, coupled with alternative computational representations, modes of interaction, and computational interfaces, to encourage public participation in planning and design. Essential to this task, is PWD’s integration of open-source, collaborative, interactive, and web-based technologies to create an online software with a visually based approach to spatial analysis and mapping that dramatically reduces the steep learning curve required for GIS software. As a high-level graphical interface, PWD allows users to iterate by intuitively creating spatial models on-the-fly based on their subjective understanding of information. In PWD, we deploy voxels, a data structure that organizes information as 3D pixels, which allows users to compute with spatial information visually, to potentially inform the ways in which users build quantitative models. In PWD, multiple layers of information can be visualized concurrently, and visual correlations can be made instantly. Users build spatial models by directly manipulating the map itself instead of manipulating a database that then produces a map. PWD’s high-level interaction is made possible by custom data structures that leverage GPU processing, which makes them significantly faster than traditional topological data structures. Computationally, user interactions generate visualization specifications and declarative queries that are compiled and executed by the platform. Lastly, PWD introduces a visual programming language, which enables intuitive geospatial modeling and visualization. Practical work has shown the value of PWD’s approach to design students, planning agencies and community non-profits. Throughout the process, PWD’s open-source spatial models generated a user community with more than 3000 users, including designers, students, and educators.

Nursing education in the age of artificial intelligence powered Chatbots (AI-Chatbots): Are we ready yet?

This article discusses the challenges and implications of artificial intelligence powered chatbot (AI-Chatbots) in nursing education. Chat Generative Pre-trained Transformer (ChatGPT) is an AI-Chatbot that can engage in detailed dialog and pass qualification tests in various fields. It can be applied for drafting course materials and administrative paperwork. Students can use it for personalized self-paced learning. AI-Chatbot technology can be applied in problem-based learning for hands-on practice experiences. There are concerns about over-reliance on the technology, including issues with plagiarism and limiting critical thinking skills. Educators must provide clear guidelines on appropriate use and emphasize the importance of critical thinking and proper citation. Educators must proactively adjust their curricula and pedagogy. AI-Chatbot technology could transform the nursing profession by aiding and streamlining administrative tasks, allowing nurses to focus on patient care. The use of AI-Chatbots to socially assist patients and for therapeutic purposes in mental health shows promise in improving well-being of patients, and potentially easing shortage and burnout for healthcare workers. AI-Chatbots can help nursing students and researchers to overcome technical barriers in nursing informatics, increasing accessibility for individuals without technical background. AI-Chatbot technology has potential in easing tasks for nurses, improving patient care, and enhancing nursing education.

Research on Innovation of Strategic Management Path of SMEs

Currently, the characteristics of small and medium-sized enterprises in China are small scale, short capital chain and weak technical background. These characteristics often put Chinese small and medium-sized enterprises at a disadvantage in market competition. In today's constantly changing market economy, a key and challenging issue for the management of small and medium-sized enterprises in China is how they can grow healthily and survive in the long term. Exploring how small and medium-sized enterprises in China can strengthen strategic management is of great significance, and this article discusses the effectiveness and innovation of this path.

Is Reviewing Valuations a Tool for Curtailment of Professional Opinions?: A Perspective of a Reviewer Based on Valuations for Secured Lending Purpose

This paper delves into the pivotal role of valuation reviews in mortgage lending, dispelling misconceptions prevalent among private practice valuers. Drawing on the International Valuation Standards Framework, the study emphasizes the importance of qualified and ethical valuers in producing credible reports. Leveraging the author's extensive experience in the state sector and as a valuation reviewer for leading banks, the paper provides insights into fourfold review techniques—Administrative (Compliance) Review, Desk Review, Field Review, and Technical Review. These techniques ensure the accuracy, appropriateness, and adherence to Generally Accepted Valuation Principles, as per International Valuation Standards. In addition, the paper explores the technical background of mortgage valuations, highlighting nine key principles followed by valuers and examining Sri Lanka Valuation Standard-07. This paper also includes ten compelling case studies, covering diverse scenarios such as legal principles, wasting assets, building limits, accuracy of calculations, and valuation challenges associated with cattle farms and apartment buildings under construction. The paper reinforces the crucial role of valuation reviews in maintaining the integrity of mortgage valuations and the inclusion of ten case studies adds practical insights, covering a spectrum of scenarios and reinforcing the argument for adherence to regulatory standards and client requirements.

How Does the Digital Transformation of Banks Improve Efficiency and Environmental, Social, and Governance Performance?

In the era of the digital economy, traditional industries have begun to realize digital transformations. For commercial banks, digital transformation is a trend and a requirement and is the only way to achieve sustainable development. At the same time, at the helm of the enterprise, executives play an essential role in the development of commercial banks. This study explored the relationship between digital bank transformation and bank efficiency, environment, society, and corporate governance (ESG) through empirical analysis, and how executives’ innovation awareness and executive technical background affect the relationships between digital bank transformation, bank efficiency, and ESG. This study used the regression method of fixed effects to conduct empirical research on the data of China’s A-share listed banks from 2011 to 2021. The research results show that the digital transformation of banks has improved efficiency and promoted the ESG performance of commercial banks. At the same time, executives’ innovation consciousness and technical background have played a positive regulatory role in banks’ digital transformation to promote bank efficiency and ESG. The main research object of this study was Chinese commercial banks. The bank’s digital transformation results were examined and the research was expanded to digital transformation and ESG. At the same time, this study has particular significance for investors who have a financial interest in banks.

INDIVIDUALIZATION IN ENGINEERING DESIGN EDUCATION: IMPLEMENTATION OF AN ADAPTIVE E-LEARNING ENVIRONMENT (ADE-LE)

AbstractWell-educated engineers are key for successful engineering design in product development. Due to varying school education and technical backgrounds, the students have different prerequisites for the acquisition of competences. Subject of this paper is to show the methodical implementation of the prototype AdE-Le suited to the curriculum at Ruhr-University-Bochum and the open source learning platform Moodle. Aim is to evaluate the didactic potential to support engineering students with heterogeneous competence levels. The general needs and existing approaches for E-Learning environments as a means to individualize learning content in engineering design are discussed. Major aim is to reduce the linkage between the students' technical background and their exam success. AdE-Le as an exemplary application is developed based on the didactical concept of Constructive Alignment. Due to a harmonization of learning methods and contents in Engineering Design across the members of the Scientific Society for Product Development the results of this investigation can be transferred to other Universities.

Geologically-Driven Migration of Landmines and Explosive Remnants of War—A Feature Focusing on the Western Balkans

Landmines and explosive remnants of war are still present in the Western Balkans and remain a deadly legacy of the hostilities at the end of the 20th century. Over the years, several incidents have occurred in Bosnia and Herzegovina, in Serbia, and in Croatia where intact ordnance has caused injuries and fatalities. Floods, torrential flows, and gravitational mass movements pose a particular threat. Landmines and explosive remnants of war are mobilized and displaced into previously uncontaminated areas. We first discuss the historical and technical background of this hazardous situation. We then show which hydro-morphological processes are responsible for the mobilization and displacement. We then illustrate how a prediction of the likely contaminated areas can be obtained. We show that the problem can only be tackled using a stochastic-deterministic model. However, for the eventual development of risk-hazard maps, preliminary work using laboratory experiments and field surveys is required. The article, therefore, proposes a novel approach to the problem in an international research project. The aim would be to produce risk-hazard maps that can be used by elected decision-makers, administrative authorities, and emergency personnel in affected municipalities.

Development and evaluation of a decision support mobile application for cotton irrigation management

Irrigation decision support tools are a means by which crop producers can improve the efficiency of water they apply. However, the available tools generally have poor adoption rates due to high costs, requirement for technical background and skills, need for extensive input data, lack of economic analysis support, and/or low accuracy. Here, we aimed to develop an inexpensive and easy-to-use decision support mobile app called Irrigation Decision-support for Conserving Resources and Optimizing Production (idCROP), to aide cotton producers in the Texas Rolling Plains and High Plains regions to increase water-use efficiency while maintaining higher crop yields. The app was built based on the crop simulation model, Decision Support System for Agrotechnology Transfer (DSSAT), and a newly developed economic model to provide real-time irrigation schedules and projected economic outcomes based on water use and production goals. The app integrates real-time management information from users with historic, real-time, and forecasted short-term and seasonal weather data. This integration enables output of efficient and situationally relevant irrigation schedules and forecasts of associated cotton yield and economic returns. This enables users to choose an irrigation strategy that best suits their irrigation capacities and expected returns. The irrigation schedules can be improved by optional remote detection of plant water stress using a sensor platform mounted on a pivot irrigation system, but the app can be used without the sensors in conjunction with any type of irrigation system. The crop model-based irrigation scheduling in idCROP was validated at the Texas A&M AgriLife Chillicothe Research Station in the Texas Rolling Plains region and acceptable results were obtained. The idCROP app provides producers with a simple but powerful tool that takes the guess work out of irrigation management, helping them apply limited irrigation water more efficiently.

Tweeting for Health Using Real-time Mining and Artificial Intelligence-Based Analytics: Design and Development of a Big Data Ecosystem for Detecting and Analyzing Misinformation on Twitter.

Digital misinformation, primarily on social media, has led to harmful and costly beliefs in the general population. Notably, these beliefs have resulted in public health crises to the detriment of governments worldwide and their citizens. However, public health officials need access to a comprehensive system capable of mining and analyzing large volumes of social media data in real time. This study aimed to design and develop a big data pipeline and ecosystem (UbiLab Misinformation Analysis System [U-MAS]) to identify and analyze false or misleading information disseminated via social media on a certain topic or set of related topics. U-MAS is a platform-independent ecosystem developed in Python that leverages the Twitter V2 application programming interface and the Elastic Stack. The U-MAS expert system has 5 major components: data extraction framework, latent Dirichlet allocation (LDA) topic model, sentiment analyzer, misinformation classification model, and Elastic Cloud deployment (indexing of data and visualizations). The data extraction framework queries the data through the Twitter V2 application programming interface, with queries identified by public health experts. The LDA topic model, sentiment analyzer, and misinformation classification model are independently trained using a small, expert-validated subset of the extracted data. These models are then incorporated into U-MAS to analyze and classify the remaining data. Finally, the analyzed data are loaded into an index in the Elastic Cloud deployment and can then be presented on dashboards with advanced visualizations and analytics pertinent to infodemiology and infoveillance analysis. U-MAS performed efficiently and accurately. Independent investigators have successfully used the system to extract significant insights into a fluoride-related health misinformation use case (2016 to 2021). The system is currently used for a vaccine hesitancy use case (2007 to 2022) and a heat wave-related illnesses use case (2011 to 2022). Each component in the system for the fluoride misinformation use case performed as expected. The data extraction framework handles large amounts of data within short periods. The LDA topic models achieved relatively high coherence values (0.54), and the predicted topics were accurate and befitting to the data. The sentiment analyzer performed at a correlation coefficient of 0.72 but could be improved in further iterations. The misinformation classifier attained a satisfactory correlation coefficient of 0.82 against expert-validated data. Moreover, the output dashboard and analytics hosted on the Elastic Cloud deployment are intuitive for researchers without a technical background and comprehensive in their visualization and analytics capabilities. In fact, the investigators of the fluoride misinformation use case have successfully used the system to extract interesting and important insights into public health, which have been published separately. The novel U-MAS pipeline has the potential to detect and analyze misleading information related to a particular topic or set of related topics.

GaNDLF: the generally nuanced deep learning framework for scalable end-to-end clinical workflows

Deep Learning (DL) has the potential to optimize machine learning in both the scientific and clinical communities. However, greater expertise is required to develop DL algorithms, and the variability of implementations hinders their reproducibility, translation, and deployment. Here we present the community-driven Generally Nuanced Deep Learning Framework (GaNDLF), with the goal of lowering these barriers. GaNDLF makes the mechanism of DL development, training, and inference more stable, reproducible, interpretable, and scalable, without requiring an extensive technical background. GaNDLF aims to provide an end-to-end solution for all DL-related tasks in computational precision medicine. We demonstrate the ability of GaNDLF to analyze both radiology and histology images, with built-in support for k-fold cross-validation, data augmentation, multiple modalities and output classes. Our quantitative performance evaluation on numerous use cases, anatomies, and computational tasks supports GaNDLF as a robust application framework for deployment in clinical workflows.

Picosecond lasers in dermatology

The picosecond laser is one of the latest laser systems in dermatology and was originally developed to optimize tattoo removal. Advances in this technology has expanded the use of the picosecond laser to numerous other indications. This article provides an overview of the technical background as well as the indications of the picosecond laser in dermatological laser medicine and elucidates the possibilities and limits of this laser system. The article is based on areview of the current literature as well as experience from clinical practice in auniversity laser department. The picosecond laser enables aparticularly gentle and effective treatment due to ultra-short pulses and the principle of laser-induced optical breakdown. Compared to Q‑switched lasers, the picosecond laser has fewer side effects and is associated with lower pain intensity and shorter downtime. In addition to the removal of tattoos and pigmentary disorders, it is also used in the treatment of scars and rejuvenation. The picosecond laser has awide range of indications in dermatological laser medicine. The current data indicate that the laser is an effective method with few side effects. Further prospective studies have to be conducted to assess the efficacy, tolerability and patient satisfaction in an evidence-based manner.

Advanced intraoperative MRI in pediatric brain tumor surgery.

Introduction: In the pediatric brain tumor surgery setting, intraoperative MRI (ioMRI) provides "real-time" imaging, allowing for evaluation of the extent of resection and detection of complications. The use of advanced MRI sequences could potentially provide additional physiological information that may aid in the preservation of healthy brain regions. This review aims to determine the added value of advanced imaging in ioMRI for pediatric brain tumor surgery compared to conventional imaging. Methods: Our systematic literature search identified relevant articles on PubMed using keywords associated with pediatrics, ioMRI, and brain tumors. The literature search was extended using the snowball technique to gather more information on advanced MRI techniques, their technical background, their use in adult ioMRI, and their use in routine pediatric brain tumor care. Results: The available literature was sparse and demonstrated that advanced sequences were used to reconstruct fibers to prevent damage to important structures, provide information on relative cerebral blood flow or abnormal metabolites, or to indicate the onset of hemorrhage or ischemic infarcts. The explorative literature search revealed developments within each advanced MRI field, such as multi-shell diffusion MRI, arterial spin labeling, and amide-proton transfer-weighted imaging, that have been studied in adult ioMRI but have not yet been applied in pediatrics. These techniques could have the potential to provide more accurate fiber tractography, information on intraoperative cerebral perfusion, and to match gadolinium-based T1w images without using a contrast agent. Conclusion: The potential added value of advanced MRI in the intraoperative setting for pediatric brain tumors is to prevent damage to important structures, to provide additional physiological or metabolic information, or to indicate the onset of postoperative changes. Current developments within various advanced ioMRI sequences are promising with regard to providing in-depth tissue information.

An integrated risk assessment modelling for cargo manifold process on tanker ships under FMECA extended Dempster–Shafer theory and rule-based Bayesian network approach

Risk assessment is one of the top requirements in maritime transportation due to the complexity of ship operations, particularly on tanker vessels. By carrying hazardous liquid cargo, tankers pose significant risks for life, property and the marine environment, which should be assessed in detail. This paper focuses on the manifold process during tanker cargo operation since it involves various risks that may lead to severe consequences such as human injury, gas poisoning, hull damage, cargo spill or explosion. The process is modelled via Bayesian network, and marine experts evaluate 12 failure modes with respect to Failure Mode, Effect and Criticality Analysis parameters. To fuse the expert judgment, Dempster–Shafer theory is applied with a rule-based approach in the Bayesian model. The highest crisp risk value is found 48.85 for Failure Mode (FM) 1.1 (Improper arrangement of valves and pipelines to be connected). It is followed by FM 1.2 (Improper connection between the line and the manifold) with a crisp risk value of 45.83, and FM 4.1 (Failure in earthing & bonding condition of equipment to be used) with 38.26 crisp risk value. According to results, control actions are presented to reduce the risks during the manifold process. Beside its technical background, the paper provides utmost contributions to maritime safety inspectors, tanker ship crew, tanker ship operators and safety researchers to improve safety process and minimize the operational risks of cargo manifold process.

Artificial Intelligence for Upper Aerodigestive Tract Endoscopy and Laryngoscopy: A Guide for Physicians and State-of-the-Art Review.

The endoscopic and laryngoscopic examination is paramount for laryngeal, oropharyngeal, nasopharyngeal, nasal, and oral cavity benign lesions and cancer evaluation. Nevertheless, upper aerodigestive tract (UADT) endoscopy is intrinsically operator-dependent and lacks objective quality standards. At present, there has been an increased interest in artificial intelligence (AI) applications in this area to support physicians during the examination, thus enhancing diagnostic performances. The relative novelty of this research field poses a challenge both for the reviewers and readers as clinicians often lack a specific technical background. Four bibliographic databases were searched: PubMed, EMBASE, Cochrane, and Google Scholar. A structured review of the current literature (up to September 2022) was performed. Search terms related to topics of AI, machine learning (ML), and deep learning (DL) in UADT endoscopy and laryngoscopy were identified and queried by 3 independent reviewers. Citations of selected studies were also evaluated to ensure comprehensiveness. Forty-one studies were included in the review. AI and computer vision techniques were used to achieve 3 fundamental tasks in this field: classification, detection, and segmentation. All papers were summarized and reviewed. This article comprehensively reviews the latest developments in the application of ML and DL in UADT endoscopy and laryngoscopy, as well as their future clinical implications. The technical basis of AI is also explained, providing guidance for nonexpert readers to allow critical appraisal of the evaluation metrics and the most relevant quality requirements.

Grounded in reality: artificial intelligence in medical education.

In a recent survey, medical students expressed eagerness to acquire competencies in the use of artificial intelligence (AI) in medicine. It is time that undergraduate medical education takes the lead in helping students develop these competencies. We propose a solution that integrates competency-driven AI instruction in medical school curriculum. We applied constructivist and backwards design principles to design online learning assignments simulating the real-world work done in the healthcare industry. Our innovative approach assumed no technical background for students, yet addressed the need for training clinicians to be ready to practice in the new digital patient care environment. This modular 4-week AI course was implemented in 2019, integrating AI with evidence-based medicine, pathology, pharmacology, tele-monitoring, quality improvement, value-based care, and patient safety. This educational innovation was tested in 2 cohorts of fourth year medical students who demonstrated an improvement in knowledge with an average quiz score of 97% and in skills with an average application assignment score of 89%. Weekly reflections revealed how students learned to transition from theory to practice of AI and how these concepts might apply to their upcoming residency training programs and future medical practice. We present an innovative product that achieves the objective of competency-based education of students regarding the role of AI in medicine. This course can be integrated in the preclinical years with a focus on foundational knowledge, vocabulary, and concepts, and in clinical years with a focus on application of core knowledge to real-world scenarios.

Utilization Of Selected Methods of Managerial Economics in Aviation Companies

The article is focused on the areas of management in aviation companies by way of applying selected methods of managerial economics, applicable under the constantly changing conditions entailing high level of risks. Attention is paid separately to the characterizing the external environment, applying the systems- based views, balance sheet analysis and controlling. The core of the publication is on selected methods representing the pillars of company economics and can be adapted by managers with purely technical background. The aviation industry is a complex and competitive market that requires companies to make strategic decisions in order to stay competitive and profitable. This paper examines the utilization of selected methods of managerial economics in aviation companies. Specifically, it explores how airlines use economic analysis to make decisions related to pricing, revenue management, cost control, and investment. The paper begins by providing an overview of managerial economics and its relevance to the aviation industry. It then explores several specific methods of managerial economics, including demand analysis, cost analysis, pricing strategies, and investment analysis. Each of these methods is discussed in detail, highlighting how they can be used to inform decision-making in aviation companies. The paper also examines case studies of successful airlines that have effectively utilized these methods of managerial economics. These case studies demonstrate how airlines have used economic analysis to optimize pricing, increase revenue, control costs, and make strategic investments. Overall, the paper concludes that the utilization of selected methods of managerial economics is crucial for the success of aviation companies. By analyzing data and making informed decisions based on economic principles, airlines can stay competitive and profitable in a constantly changing market. As such, the paper provides a valuable resource for aviation managers and researchers seeking to better understand the role of economics in the aviation industry. Keywords - Economics, management, levels of control, methods of economical analysis, managerial skills

Abstract 5409: NuKit: a deep learning platform for histopathological Images

Abstract Hematoxylin and eosin (H&E) staining is the most common type of histopathological images used for quantitative data analysis. For histopathological image analysis, nucleus segmentation represents one of the initial steps in quantitative data analysis pipelines. Recently, deep learning methods for nucleus segmentation on histopathological images become the mainstream in digital pathology. However, adopting these pre-trained models in digital pathology or clinical research remains limited. Two main factors limit the usage of deep learning methods in routine research: 1) many models required some technical background to execute the programs, and 2) the speed of returning the results to the users. To overcome these limitations, we have developed and implemented NuKit, a deep learning platform which accelerates nucleus segmentation and provides prompt results to the users. NuKit platform consists of two deep learning models coupled with an interactive graphical user interface (GUI) to provide fast and automatic nucleus segmentation “on the fly”. The two deep learning models are: 1) the whole image segmentation model and 2) the click segmentation model. Both deep learning models provide complementary tasks in nucleus segmentation in the NuKit platform. The whole image segmentation model performs whole image nucleus whereas the click segmentation model supplements the nucleus segmentation with user-driven input to edits the segmented nuclei. We used PanNuke as the training data set which contains 160,368 nuclei extracted from 7,901 image tiles. The sources of this data set were curated from The Cancer Genome Atlas (TCGA) and included a very few in-house data. For test sets, we used several popular data sets such as TCGA (not used in the training set). We used DICE coefficient as the metric for comparisons of NuKit with other deep learning methods. For the results, we observed that NuKit achieved comparable results with the state-of-the-art deep learning methods and outperforms those non-deep learning methods. For TNBC and CoNSeP data sets, NuKit achieved DICE 0.793 and 0.854 comparing to HoVer-Net 0.749 and 0.664. For CoNSeP test data set, NuKit achieved DICE 0.860 comparing to Cell Profiler 0.434 and QuPath 0.588. In addition, both pre-trained models were embedded in the NuKit GUI, which provides interactive and prompt response to users in analyzing their histopathological images. The outputs of NuKit are interoperable with other quantitative image analysis tools to facilitate the ecosystem of computational pathology to many formats to combine with other software to construct pipelines. In summary, we have introduced NuKit, an innovation platform which combines two deep learning models coupled with interactive GUI to accelerate nucleus segmentation task in histopathological images. We believe that NuKit provides a new platform to bridge the pre-trained deep learning models into digital pathology and clinical usage. Citation Format: Ching-Nung Lin, Christine H. Chung, Aik Choon Tan. NuKit: a deep learning platform for histopathological Images. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5409.

Problems and countermeasures of accounting informatization construction in colleges and universities under the background of big data and artificial intelligence

As the scale of online socialization continues to expand, the amount of data generated by people’s social networking continues to increase, and data has gradually become the invisible wealth of various industries, and data analysis, as the main method to control data, has become a skill that must be mastered in the development of talents in various industries. Big data technology is a data storage and processing method based on data analysis technology. Prediction of the law of development of a certain thing and analysis of the success rate of a certain decision. Big data technology has played an important role in the informatization of various industries, and its use in accounting informatization can bring more convenience to accounting work. Although artificial intelligence technology has only been born for less than a hundred years, the technical branches it has developed have been widely used in various industries. At present, the types of algorithms corresponding to artificial intelligence technology are still increasing, and the application of AI algorithms to the development of accounting informatization can make Accounting work is more intelligent, and its accuracy can be improved on the basis of greatly reducing labor costs. Putting the construction of accounting informatization in colleges and universities under the technical background of artificial intelligence and big data development can achieve more valuable breakthroughs in data collection and countermeasure optimization. This paper first analyzes the theories of big data, artificial intelligence and accounting informatization, and then obtains various problems existing in the development of accounting informatization construction in colleges and universities through questionnaires. By comparing the newly designed solutions with the traditional accounting informatization construction solutions, it is found that the accounting informatization construction solutions combined with big data and artificial intelligence can be used in accounting personnel training, accounting platform security hidden danger investigation and college accounting. Internal control and other directions are superior to the traditional accounting informatization construction plan.