Automatic Software Research Articles

Technology management competencies of library and information science professionals: insights from Pakistan

Purpose This study aims to examine the technology management skills of library and information science (LIS) professionals in Khyber Pakhtunkhwa’s college libraries, emphasizing their knowledge of operating systems, library management systems and application software. It also identified challenges and training needs for skill enhancement. Design/methodology/approach The study used a quantitative approach encompassing the entire population of 155 library heads, using a census-based approach and analyzed the data using the Statistical Package for Social Sciences. Findings The findings demonstrated that while most participants were competent in operating Windows and Linux operating systems, their knowledge of Unix could be improved. They demonstrated proficiency in automation software, and with the proper support, they could have enhanced their competencies in repository software. Their skills in using application software like the Microsoft Office suite and Photoshop were commendable, and with exposure, they could have broadened their familiarity with various web applications. The significant problems identified were the absence of interest in learning IT knowledge, economic difficulties, limited opportunities, strict working schedules and the absence of in-service training provisions. Practical implications The study reveals that professionals need additional training to enhance their competencies, leading to improved service efficiency and effectiveness. It also highlights the need for authorities to prioritize funding for training initiatives. Originality/value This study offers insights into LIS technology management competencies, identifying gaps and challenges. It proposes innovative solutions to improve efficiency, promote digital inclusion and provide practical recommendations for navigating the evolving landscape.

Development of Artificial Intelligence-based Real-time Automatic Fusion of Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasonography of the Prostate.

To report the development of artificial intelligence (AI)-based software to allow for the autonomous fusion of transrectal ultrasound and multiparametric magnetic resonance images of the prostate to be used during transperineal prostate biopsies. This study was approved by the Institutional Review Board (protocol ID 3167CESC). The automatic software development for fusion biopsy involved 3 steps: (1) developing an AI component to segment the prostate during ultrasound; (2) developing the component to segment anatomical structures in magnetic resonance images using labeled datasets from the Cancer Imaging Archive and in-house scans; (3) developing the fusion component to register segmented ultrasound and magnetic resonance images using a 3-step process: pre-alignment, rigid alignment, and elastic fusion, validated by measuring the lesion distance between modalities. Statistical analysis included descriptive statistics and the Mann-Whitney U test, evaluating outcomes with Dice scores and average precision metrics. The ultrasound component showed a Dice score of 0.87 with a test set of 75,357 images and 28,946 annotations. The magnetic resonance component achieved a Dice score of 0.85 on a test set of 2494 images and annotations. It also demonstrated a mean average precision of 0.80 for bounding boxes and 0.88 for segmented objects, both measured at a 50% intersection over union threshold. The fusion AI component reduced the median magnetic resonance-ultrasound lesion distance from 8mm (interquartile ranges 6-9) after rigid fusion to 4mm (interquartile ranges 3-5) after elastic fusion (P<.001). A data processing pipeline and AI were created to allow for the autonomous fusion of ultrasound and magnetic resonance images to be ideally used during transperineal prostate biopsies.

AI in QA: Transforming test automation and software quality through intelligent solutions

Artificial intelligence is revolutionizing quality assurance processes in the rapidly evolving software development landscape, offering unprecedented enhancements to test automation and overall software quality. This technical article explores the transformative impact of AI across multiple dimensions of QA, including test case generation based on user behavior analytics, self-healing test automation frameworks that adapt to UI changes, advanced defect prediction systems that identify high-risk code modifications, and computer vision applications for visual regression testing. The article provides a comprehensive analysis of current capabilities and implementation strategies by examining industry-leading tools such as Testim, Applitools, Selenium with Healenium, and SonarQube with AI anomaly detection; the discussion culminates in a real-world enterprise case study demonstrating significant efficiency improvements, offering readers practical insights for integrating AI-powered testing methodologies into their development workflows.

Use of Library Automation Software in Engineering College Libraries in Vidarbha Region: A Study

Abstract: This paper examines the use of library automation software in engineering college libraries in Vidarbha. A structured questionnaire was used to collect primary information from college libraries to understand the current status. A total of 60 engineering colleges were surveyed for this study, out of which 55 (91.66%) responded, while 5 college libraries did not respond. The findings of the study show that most of the autonomous colleges are automated. The findings of the study show that 26 (47.3%) college libraries have been automated. Out of these, 40.0% of the libraries using open source software have adopted ‘open source’ library automation software. The librarian should take the initiative, connect with others and professionally support the library for its development and up gradation of its skills. Keywords: Library Automation, Engineering Library, Automation Software, Vidarbha

Enhancing Radiologist Productivity with Artificial Intelligence in Magnetic Resonance Imaging (MRI): A Narrative Review.

Artificial intelligence (AI) shows promise in streamlining MRI workflows by reducing radiologists' workload and improving diagnostic accuracy. Despite MRI's extensive clinical use, systematic evaluation of AI-driven productivity gains in MRI remains limited. This review addresses that gap by synthesizing evidence on how AI can shorten scanning and reading times, optimize worklist triage, and automate segmentation. On 15 November 2024, we searched PubMed, EMBASE, MEDLINE, Web of Science, Google Scholar, and Cochrane Library for English-language studies published between 2000 and 15 November 2024, focusing on AI applications in MRI. Additional searches of grey literature were conducted. After screening for relevance and full-text review, 67 studies met inclusion criteria. Extracted data included study design, AI techniques, and productivity-related outcomes such as time savings and diagnostic accuracy. The included studies were categorized into five themes: reducing scan times, automating segmentation, optimizing workflow, decreasing reading times, and general time-saving or workload reduction. Convolutional neural networks (CNNs), especially architectures like ResNet and U-Net, were commonly used for tasks ranging from segmentation to automated reporting. A few studies also explored machine learning-based automation software and, more recently, large language models. Although most demonstrated gains in efficiency and accuracy, limited external validation and dataset heterogeneity could reduce broader adoption. AI applications in MRI offer potential to enhance radiologist productivity, mainly through accelerated scans, automated segmentation, and streamlined workflows. Further research, including prospective validation and standardized metrics, is needed to enable safe, efficient, and equitable deployment of AI tools in clinical MRI practice.

Systematic comparison of Commercial seizure detection Software: Update equals Upgrade?

Systematic comparison of Commercial seizure detection Software: Update equals Upgrade?

Abstract 6039: Triads of dendritic cells, CD4+ T cells, and CD8+ T cells are found within PDA tumors and are associated with intrinsic anti-tumor immune responses

Abstract Cytotoxic T cells (CTLs) are the main effectors of anti-tumor immunity, and their activation is dependent on carefully coordinated interactions between antigen presenting cells (APCs) and CD4+ T cells (Th). In a pivotal model, synchronized interaction between a dendritic cell (DC), Th, and CTL were posited as requisite for effective CTL responses. Recent studies have resurrected this hypothesis in the context of anti-tumor immunity and demonstrated the function of 3 cell type clusters in immune checkpoint blockade (ICB) response in murine tumors and human cancer. We hypothesized intratumoral 3-cell type clusters are present in an “immune excluded tumor”, pancreatic adenocarcinoma (PDA), outside the context of immunotherapy. Analysis of single cell RNAseq and PDA tumors identified DC:Th:CTL clusters, defined as DC, Th, and CTL within 20µm radius, occurring with ∼15% of DCs. Analysis of multiplex proteomics data from fibrolamellar carcinoma, a rare stromal dominant liver tumor with poor immune infiltration, revealed the presence of DC:Th:CTL clusters. We sought to confirm our findings in a larger dataset using multiplex immunohistochemistry (mIHC) on a tissue microarray (TMA) of &amp;gt;500 patients with untreated resected PDA. Using automatic image analysis software, we identified cell types based on surface marker expression, specifically tumor cells, CTL, Th, macrophages, and non-macrophage APCs. 3-cell type clusters were found in 90% of tumor samples, occurred with ∼10% of APCs, located &amp;gt;50µm from tumor cells, and correlated strongly with APC:Th dyads. Weak correlation was found between 3-cell type clusters and isolated cell types, suggesting cluster formation is unlikely to be related to abundance of infiltrating immune cells. DC:Th:CTL clusters were also readily seen in scST of untreated non-small cell lung cancer (NSCLC) and colorectal cancer (CRC). Analysis of PDA, NSCLC, and CRC scST datasets revealed that CTLs within triads were more likely to have an effector-like phenotype. Th within triads were enriched in CXCL13+-like Th phenotype, which previously has been associated with immune triads. Using associated clinical data in the PDA TMA, we found that patients with the highest tertile of APC:Th:CTL clusters had improved overall survival compared to patients with the lowest tertile (HR=0.70, p=0.005). Similar findings were found for patients with the top tertile of APC:Th dyads (HR=0.63, p=6.x10-4), but not APC:CTL or CTL:Th dyads (HR=0.76 and 0.77 and p=0.16 and 0.07, respectively). Overall, our findings demonstrate 3-cell type clusters are readily found in an “immune excluded” tumor like PDA without immunotherapy and are associated with improved patient outcomes. These data are strong evidence for the role of 3-cell type clusters in endogenous anti-tumor immune responses and point toward future opportunities for immunotherapeutic intervention. Citation Format: Sheela R. Damle, Jason A. Carter, Jose M. Pineda, Kristin E. Goodsell, Lindsay K. Dickerson, Shreeram Akilesh, Ian N. Crispe, Venu G. Pillarisetty. Triads of dendritic cells, CD4+ T cells, and CD8+ T cells are found within PDA tumors and are associated with intrinsic anti-tumor immune responses [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 6039.

An automatic software test-generation method to discover the faults using fusion of machine learning and horse herd algorithm

One of the time-consuming and expensive phases in software development is software testing, which is used to improve the quality of software systems. Therefore, Software test automation is a helpful technique that can alleviate testing time. Several techniques based on evolutionary and heuristic algorithms have been put forth to produce maximum coverage test sets. The primary shortcomings of earlier methods are inconsistent outcomes, insufficient branch coverage, and low fault-detection rates. Increasing branch coverage rate, defect detection rate, success rate, and stability are the primary goals of this research. A time- and cost-effective method has been suggested in this research to produce test data automatically by utilizing machine learning and horse herd optimization algorithms. In the first stage of the proposed method, the suggested machine learning classification model identifies the non-error-propagating instructions of the input program using machine learning algorithms. In the second stage, a test generator was suggested to cover only the program's fault-propagating instructions. The main characteristics of produced test data are avoiding the coverage of non-error-propagating instructions, maximizing the coverage of error-propagating instructions, maximizing success rate, and the fault discovery capability. Several experiments have been performed using nine standard benchmark programs. In the first stage, the suggested instruction classifier provides 90% accuracy and 82% precision. In the second stage, according to the results, the produced test data by the suggested method cover 99.93% of the error-prone instructions. The average success percentage with this method was 98.93%. The suggested method identifies roughly 89.40% of the injected faults by mutation testing tools.

Nano FPV Surveillance Drone

The advancement in technology has shifted the way we approach security and surveillance. Among the latest innovations in this field is the Nano FPV (First Person View) Surveillance Drone, a small yet powerful tool designed to enhance monitoring capabilities. Presently, Unmanned Aerial Vehicles (UAVs) or drones are employed in a wide range of operations, especially in surveillance systems. Drone surveillance involves visually monitoring an individual, a group, items, or a situation to prevent potential threats. The establishment of an efficient surveillance system with drone fleets necessitate the smooth integration of dependable hardware and sophisticated automation software. The Nano FPV (First-Person View) Surveillance Drone represents a significant advancement in the field of unmanned aerial vehicles (UAVs). Keywords- First Person View (FPV) Drones, Nano drones, Unmanned Aerial Vehicles (UAV), Quadcopter, Surveillance UAV, Real-time video transmission, Environment Monitoring.

ADNA: Automating Application-Specific Integrated Circuit Development of Neural Network Accelerators

Recently, multiple new technologies have emerged for automating the development of neural network (NN) accelerators for both field-programmable gate arrays (FPGAs) and application-specific integrated circuits (ASICs). This paper explores methodologies for translating NN algorithms into chip layouts, with a focus on end-to-end automation, cost-effectiveness, and open-source software. We present a robust framework for developing NN-to-silicon solutions and demonstrate a seamless plug-and-play automation flow using TensorFlow, Vivado HLS, HLS4ML, and Openlane2. SkyWater Technologies’ 130 nm PDK (Sky130) is employed to successfully generate layouts for two small NN examples under 1000 parameters, incorporating dense, activation, and 2D convolution layers. The results affirm that current open-source tools effectively automate low-complexity neural network architectures and deliver faster performance through FPGA structures. However, this improved performance comes at the cost of increased die area compared to bare-metal designs. While this showcases significant progress in accessible NN automation, achieving manufacturing-ready layouts for more complex NN architectures remains a challenge due to current tool limitations and heightened computational demands, which points to exciting opportunities for future advancements.

Redesigning CMOS VLSI using Yosys synthesis tool

Objectives. The problem of reverse engineering of a transistor level circuit specified in the SPICE format in a different technological basis is considered. The goal of the work is to develop an approach to redesigning circuits using open source design automation software packages.Methods. A method is proposed based on extracting the structure at the level of logical elements from a flat SPICE description of a transistor circuit and exporting the resulting hierarchical SPICE description to the software environment of the open synthesis package Yosys. The purpose of the export is to transform the description of the logical network in the SPICE format into descriptions in the input languages of design automation systems, as well as to perform optimization and synthesis operations in the Yosys environment.Results. To export a logical network specified in the SPICE format to the core of the Yosys package, a program in C++ was developed using the classes of the Yosys package. The program accepts and processes the hierarchical SPICE description of the logical network, translating it into a representation in the internal format of the Yosys tool.Conclusion. The developed program is designed as a Yosys program module and integrated into its environment as one of its commands. All the transformations available in Yosys can be performed on the logical network structure obtained by the module.

Automated Software Analysis and Documentation Generator

Software complexity compels the use of advanced tools for automated code analysis and documentation. In the traditional approach to understand the large code base, human effort is undeniably needed, thus time-consuming, error-prone, and expensive. This paper will present an overall framework for automatic software analysis and generation of documentation. The framework, building on the versatility of Python libraries for the scanning of directories, parsing of syntax trees, visualization of control flows, and concurrent processing, enables the rapid understanding of software architecture and functionality. It supports a range of programming languages and automatically produces structured documentation, such as flowcharts, UML diagrams, and detailed reports. In summary, it is a solution that should improve software maintainability, increase code comprehension, and sustain research in software analysis

METHODS FOR INTEGRATING ARTIFICIAL INTELLIGENCE AND KNOWLEDGE ENGINEERING INTO AUTOMATON-BASED REAL-TIME SOFTWARE SYSTEMS

The continuous evolution of software systems necessitates the integration of Artificial Intelligence (AI) and knowledge engineering to enhance automation, adaptability, and real-time decision-making. Traditional software solutions often struggle to meet the increasing demands for dynamic, autonomous, and intelligent functionalities, particularly in real-time applications where responsiveness and contextual awareness are critical. This paper explores the development of AI-enhanced automated software systems, focusing on their implementation in environments that require high levels of interaction and adaptability. The proposed approach leverages cloud-based AI services, particularly Azure OpenAI, to enhance system responsiveness through the integration of advanced natural language processing (NLP), dialogue management, and decision-making algorithms. By utilizing AI models such as generative pre-trained transformers (GPT), the system is capable of understanding complex user queries, maintaining contextual coherence in conversations, and autonomously executing tasks with minimal human intervention. A key aspect of this research is the architectural framework designed to facilitate seamless interaction between AI components and external systems, ensuring real-time data processing and decision optimization. One of the core contributions of this study is demonstrating how AI-driven automation can significantly enhance the efficiency and reliability of real-time software applications. Case studies and examples illustrate the practical implementation of these technologies in enhancing user experience and operational efficiency. Evaluation metrics encompass performance indicators for AI-driven functionalities, ensuring scalability and reliability in dynamic environments. The paper also discusses future development prospects and potential challenges in the field, emphasizing the need for continuous adaptation and improvement of AI-driven software systems in line with modern technological trends and user requirements.

FP6.7 Constructing Large-Scale 3D Hip Morphology Database of Normal Hip Development Using Multi-Modal Artificial Intelligence Tools

Abstract Introduction: Hip morphology has significant role in a range of hip pathologies. While some of these anatomical features can be readily measured from plane films, the more complex and clinically significant dysmorphologies require 3D evaluations (e.g., from CT or MRI). Comprehensive 3D evaluation of hip morphology is cumbersome and often neglected clinically. Moreover, there is a lack of population-specific thresholds for those assessments as the existing data is based on 2D measurements from X-Ray images and are not directly translatable to 3D assessments. Here we aimed to use multi-modal AI pipelines to generate a comprehensive registry of normal hip development during skeletal development and maturation form a large dataset of clinical CT scans at a tertiary-care children’s hospital. Methods: Following IRB approval, we identified all the abdominal/pelvic/hip scans done at our institute between 2012-2020. We then developed a multi-modal pipeline to automatically: 1) identify any documented hip pathologies in the radiology reports using natural language processing (NLP), 2) reconstruct 3D models of the hip bones and identify anatomical landmarks using convolutional neural networks and deep learning, and 3) to measure hip anatomy in 3D using a custom and validated automatic software. Results: The NLP pipeline achieved an accuracy of 0.98 in identifying hip pathology from radiology reports. The 3D reconstruction and landmark detection pipeline resulted in average Dice coefficient of 0.98±0.03 and average surface error of &amp;lt;1 mm. The morphology measurement pipeline resulted in an average error of &amp;lt;2 mm and &amp;lt;6 degrees. From a total of 52,360 CT scans, we identified and analyzed 9,721 “good quality” normal CT scans (49.3% Females; Age: 7 to 25 years, average: 14 4 years; 19,442 hips). On average, females had smaller femoral heads, epiphyseal tubercle, femoral necks, acetabulum, and alpha angles along with greater peripheral cupping, coronal head-neck tilt, femoral head-neck offset, overall femoral head coverage, acetabular anteversion, and posterior-superior center-edge angles (P&amp;lt;0.001). There were no clinically meaningful sex-differences in anterior-superior center-edge angles and sacro-pelvic sagittal alignments. Summary/Clinical Significance: The current project highlights the feasibility of multi-modal approaches to process existing clinical data to generate large-scale registries, which can then be used to improve care through evidence-based personalized diagnosis and treatment planning. This rich database is currently being used to develop normative growth charts for detailed anatomical features of the hip throughout the skeletal growth and maturation. We are planning to publicly release this data to assist with personalized assessment of hip dysmorphology.

Relationship between White Matter Hyperintensity Volume Analyzed from Fluid-Attenuated Inversion Recovery Using a Fully Automated Analysis Software and Cognitive Impairment

Introduction: White matter hyperintensity (WMH) is associated with cognitive impairment, although the clinical significance of WMH remains unclear. We aimed to elucidate the clinical significance of WMH volume and whether a fully automated quantitative analysis of WMH would be an effective marker of cognitive function. Methods: Patients with suspected cognitive impairment were retrospectively examined. Clinical data, including patient information, neuropsychological examinations, diagnoses of dementia disorders, and fluid-attenuated inversion recovery (FLAIR) images, were collected. Patient information included sex, age, and educational level. Neuropsychological examinations included the Mini-Mental State Examination (MMSE) and Japanese version of the Montreal Cognitive Assessment (MoCA-J). WMH volumes were analyzed from FLAIR images using a fully automatic analysis software. The relationship between WMH volume and clinical data was investigated. Results: WMH volume was analyzed using 889 FLAIR cases. The WMH volume did not differ significantly between the sexes. WMH volume showed a positive correlation with age. Multiple comparison tests showed no significant difference in WMH volume between junior high school and high school graduates, but all other differences were significant. Multiple comparison tests revealed significant differences in mean WMH volume among all groups in the classified MMSE. The Mann-Whitney U test revealed significant differences in WMH volume between the two groups. Multiple comparison tests revealed significant differences in WMH volume among all the groups of classified diagnostic results. Conclusion: Quantitative analysis of WMH volume from FLAIR images may provide useful information for dementia treatment and may be effective as a new marker in cognitive function examinations.

The impact of financial technology on bank’s performance in Egypt: the moderating role of COVID-19 pandemic

Purpose The study aims to examine the moderating role of COVID-19 in the effect of financial technology on bank performance in the Egyptian banking sector. Design/methodology/approach The study uses a panel regression model, estimated using a fixed-effects approach, for the period spanning 2016–2022. Findings The study reveals a significant positive effect of financial technology on bank performance. In contrast, control variables such as the inflation rate and firm size show no notable impact on performance. Conversely, the annual gross domestic product growth rate exhibits a positive and significant influence on bank performance. Furthermore, COVID-19 moderates the relationship between the cost of software automation and variables such as capital adequacy (CA), asset quality (AQ) and liquidity, as well as the relationship between ATM machines and liquidity. However, it does not affect the relationship between the number of credit cards and any performance metrics. Research limitations/implications The study focuses exclusively on one country, Egypt and one industry, banking. Other financial institutions, such as insurance companies, leasing companies and investment trusts, are not included in this analysis. Practical implications The results confirm the policymakers should encourage collaboration between banks and fintech firms by relaxing regulatory constraints and providing incentives for mergers and acquisitions, which can generate significant synergies within the banking sector. Originality/value To the best of the authors’ knowledge, this is the first study to examine the impact of financial technology on bank performance using five different measures: CA, AQ, earnings, liquidity management and financial stability.

Development and Practical Application of AI Automatic Wipe Editing Software "FALCON"

Development and Practical Application of AI Automatic Wipe Editing Software "FALCON"

Association between remnant cholesterol and culprit vessel physiological features in patients with acute coronary syndrome: An optical coherence tomography study.

Association between remnant cholesterol and culprit vessel physiological features in patients with acute coronary syndrome: An optical coherence tomography study.

Study on automatic contour delineation of organs at risk in intensity-modulated radiotherapy for nasopharyngeal carcinoma

Objective: To compare the efficiency and accuracy of contour delineation of organs at risk (OARs) in intensity modulated radiotherapy (IMRT) for nasopharyngeal carcinoma (NPC) between a homemade automatic contouring software (Yorktal-CS 1.0) and two commercial radiotherapy treatment planning system (TPS). Methods: A total of 100 NPC patients who underwent IMRT in five hospitals of different levels in Chongqing from January 1, 2016 to December 31, 2018 were enrolled. 12 OARs of NPC radiotherapy were contoured using Yorktal-CS 1.0, while 2 commercial TPSs (Eclipse and Qi-Lin), were used as controls. Time elapsed during contour delineation was recorded for comparison and the quality of automatic contour delineation was analyzed by Dice Similarity Coefficient (DSC). Results: The median duration of contour delineation in 12 OARs of NPC patients using Yorktal-CS 1.0 was 225.33 seconds, which was significantly (P = 0.000) shorter than that using Eclipse (1081.31 seconds) and Qi-Lin (1945.80 seconds). In terms of accuracy, the median DSC of Yorktal-CS 1.0 automatic contour delineation in 12 OARs ranged between 0.76 and 0.90. The maximum DSC value was 0.94 in bilateral eyeballs, while the minimum value was 0.66 found in the oral cavity. It should be noted that manual inspection and modification must be performed after automatic contour delineation and the duration of Yorktal-CS 1.0 depicted here included both automatic contour delineation and manual modification. Conclusion: In this study, Yorktal-CS 1.0 can greatly improve the efficiency of contour delineation while ensuring contouring accuracy, showing superiority to commercially available TPSs. The Yorktal-CS 1.0 could reduce the workload of radiologists and improve the efficiency of radiotherapy, which could be a promising tool for clinical application.

PSLSA v2.0: An automatic Python package integrating machine learning models for regional landslide susceptibility assessment

PSLSA v2.0: An automatic Python package integrating machine learning models for regional landslide susceptibility assessment