Visual Insight Research Articles

XAI Heart Disease Prediction

Abstract This project presents a lightweight and interactive web application designed to predict the likelihood of heart disease using clinical parameters. Built using Streamlit, the application leverages a machine learning classification model trained on the widely used Cleveland Heart Disease dataset. To enhance model transparency and trustworthiness, SHAP (SHapley Additive exPlanations) has been integrated, providing users with clear and intuitive visual insights into how each input feature contributes to the prediction. The aim is to create a tool that is not only accurate but also interpretable, helping both developers and potential users understand the logic behind each outcome. The project emphasizes accessibility, explainability, and the practical application of machine learning in the healthcare domain. Keywords- “Heart disease prediction”,”SHAP”,”Streamlit”, ”Machine learning”,” Explainable AI”

The Pharmaceutical Production of Tibetan Medicines

Abstract This photo essay documents the pharmaceutical production process of Tibetan medicine at the Dharamsala Men-Tsee-Khang in India. Tracing Tibetan medicine-making from the pharmacy gate to the clinics, and from the acquisition of medicinal raw materials to the prescription of pills, it offers rare visual and ethnographic insights into the largely invisible core of contemporary Tibetan medicine and its industry. By highlighting the expertise and experience required for Tibetan medicine production today, this essay underscores the complexity and sophistication of Tibetan pharmaceutical manufacturing in an industrial context.

Insight predicts subsequent memory via cortical representational change and hippocampal activity

The neural mechanisms driving creative problem-solving, including representational change and its relation to memory, still remain largely unknown. We focus on the creative process of insight, wherein rapid knowledge reorganization and integration—termed representational change—yield solutions that evoke suddenness, certainty, positive emotion, and enduring memory. We posit that this process is associated with stronger shifts in activation patterns within brain regions housing solution-relevant information, including the visual cortex for visual problems, alongside regions linked to feelings of emotion, suddenness and subsequent memory. To test this, we collect participants’ brain activity while they solve visual insight problems in the MRI. Our findings substantiate these hypotheses, revealing stronger representational changes in visual cortex, coupled with activations in the amygdala and hippocampus—forming an interconnected network. Importantly, representational change and hippocampal effects are positively associated with subsequent memory. This study provides evidence of an integrated insight mechanism influencing memory.

FRACTIONAL VIEW ANALYSIS OF THE DYNAMICS OF A PLANT DISEASE THROUGH CAPUTO–FABRIZIO DERIVATIVE

A thorough understanding of the dynamics of cotton leaf curl virus (CLCuV) disease is crucial for developing effective control strategies, mitigating economic losses in cotton production, and ensuring sustainable agriculture in regions affected by this infection. In this work, we formulate the dynamics of CLCuV disease in a fractional framework to capture the intricate phenomena associated with the disease. The infection-free steady state of the model is determined, and the reproduction parameter is determined by applying the next-generation matrix approach, indicated by [Formula: see text]. Our results reveal that the infection-free equilibrium exhibits local asymptotic stability when [Formula: see text], and unstable when it exceeds the threshold. We establish the existence and uniqueness of the solution for our recommended model of the disease. In addition to this, we explore the dynamical behavior through numerical results, aiming to elucidate the complex dynamics of the disease and provide visual insights into key determinants. This knowledge facilitates the development of efficient disease management strategies, such as the prompt implementation of control measures, the creation of resistant varieties, and the enhancement of cultural customs. Finally, a thorough understanding of the disease dynamics empowers farmers and authorities to adopt proactive measures, reducing the economic losses and preserving the health of cotton crops.

Integrating local and global attention mechanisms for enhanced oral cancer detection and explainability.

Integrating local and global attention mechanisms for enhanced oral cancer detection and explainability.

Antarctic lichens exhibit diverse photobiont distributions and a complex regulation of non-photochemical quenching.

Antarctic lichens exhibit diverse photobiont distributions and a complex regulation of non-photochemical quenching.

Explorative 3-D culture of early secondary follicles in a time lapse system for up to 36 days gives valuable, but limited insights in follicular development.

Explorative 3-D culture of early secondary follicles in a time lapse system for up to 36 days gives valuable, but limited insights in follicular development.

Machine learning-based prediction of the necessity for the surgical treatment of distal radius fractures

BackgroundTreatments for distal radius fractures (DRFs) are determined by various factors. Therefore, quantitative or qualitative tools have been introduced to assist in deciding the treatment approach. This study aimed to develop a machine learning (ML) model that determines the need for surgical treatment in patients with DRFs using a ML model that incorporates various clinical data concatenated with plain radiographs in the anteroposterior and lateral views.MethodsRadiographic and clinical data from 1,139 patients were collected and used to train the ML models. To analyze and integrate data effectively, the proposed ML model was mainly composed of a U-Net-based image feature extractor for radiographs, a multilayer perceptron based clinical feature extractor for clinical data, and a final classifier that combined the extracted features to predict the necessity of surgical treatment. To promote interpretability and support clinical adoption, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to provide visual insights into the radiographic data. SHapley Additive exPlanations (SHAP) were utilized to elucidate the contributions of each clinical feature to the predictions of the model.ResultsThe model integrating image and clinical data achieved accuracy, sensitivity, and specificity of 92.98%, 93.28%, and 92.55%, respectively, in predicting the need for surgical treatment in patients with DRFs. These findings demonstrate the enhanced performance of the integrated model compared to the image-only model. In the Grad-CAM heatmaps, key regions such as the radiocarpal joint, volar, and dorsal cortex of the radial metaphysis were highlighted, indicating critical areas for model training. The SHAP results indicated that being female and having subsequent or concomitant fractures were strongly associated with the need for surgical treatment.ConclusionsThe proposed ML models may assist in assessing the need for surgical treatment in patients with DRFs. By improving the accuracy of treatment decisions, this model may enhance the success rate of fracture treatments, guiding clinical decisions and improving efficiency in clinical settings.

A Phishing URL Detection Tool PhishGuard Using Python

PhishGuard is an API-based security tool that uses machine learning algorithms to identify and analyze phishing URLs, complemented by the VirusTotal API for full-fledged risk analysis. The tool maximizes its analytical power by integrating machine learning (ML) algorithms for automated URL extraction, analysis, and reporting, giving users useful details regarding the possible danger level of suspicious URLs. Some of the major features are automatic URL scanning by a mere keyboard shortcut (Shift + Click), live analysis of phishing likelihood optimized by ML-based predictions, and PDF report generation with detailed information. PhishGuard also provides visual insights in the form of pie charts, classifying URLs according to their risk levels. All scanned URLs are logged by the system and stored in categorized log files for future use. Developed with Python, PhishGuard combines technologies like Matplotlib for visualization, PyQt6 for the interface, and FPDF for report generation. PhishGuard is made to be easy to use, with simple installation and uninstallation procedures. PhishGuard seeks to improve browsing security by giving users a safe and efficient way of detecting and avoiding malicious URLs using the power of machine learning.

Ratiometric Dual-Response Quantum Dot Spherical Nucleic Acid for Monitoring Viral Secondary Bacterial Infections.

Viral-bacterial coinfections present intricate pathologies that exacerbate disease progression and elevate mortality rates. Understanding the dynamic interplay between viruses and bacteria during coinfection is critical for developing effective therapeutic interventions. However, current diagnostic tools primarily rely on static detection methods, limiting their ability to monitor real-time infection dynamics. Here, we introduce a ratiometric, dual-responsive quantum dot spherical nucleic acid (QD-SNA) probe capable of simultaneously detecting viral- and bacterial-specific markers in vivo. This probe enables real-time monitoring of coinfections, as demonstrated in a mouse model of influenza virus (H1N1) and methicillin-resistant Staphylococcus aureus infection. By providing dynamic, visual insights into the coinfection process, the QD-SNA probe holds significant potential for preclinical drug screening and the diagnosis of respiratory pathogen infections.

Automated Visual Insight via AI-Based Processing

Artificial Intelligence (AI) has revolutionized image processing by enhancing automation, accuracy, and efficiency across various domains such as medical diagnostics, autonomous vehicles, security, agriculture, and entertainment. Traditional image processing techniques relied on rule-based algorithms, which had limitations in complex scenarios. AI-powered image processing leverages deep learning models,neural networks, and computer vision techniques to analyze and manipulate images with human-like intelligence. This paper provides an in-depth analysis of AI-driven image processing, covering fundamental techniques, applications, challenges, and future trends

AgroVision AI

Agriculture remains the backbone of India's economy, yet farmers continue to face challenges related to unpredictable crop prices, inefficient water usage, climate variability, and lack of actionable market intelligence. AgroVision AI is an integrated, AI-powered agricultural intelligence platform designed to empower farmers with data-driven insights. Leveraging advanced machine learning models such as LSTM and CatBoost, AgroVision AI predicts crop prices, recommends efficient irrigation schedules, offers precise crop health analysis, and provides real-time weather forecasting. The platform integrates external APIs for dynamic market price updates and weather conditions, while delivering user-friendly dashboards and visual insights through a modern web interface. By synthesizing market trends, soil conditions, climatic factors, and historical data, AgroVision AI enhances agricultural decision-making, optimizes resources, and maximizes profitability for farmers. This research paper presents the design, methodology, and potential impact of AgroVision AI in revolutionizing the agricultural ecosystem through predictive analytics and smart farming technologies.

Manufacture of AZ91 Mg alloy with a superhydrophobic surface using a combination of electrodeposition and chemical dealloying

ABSTRACT Superhydrophobic (SH) coatings with micro/nano hierarchical structures on AZ91 Mg alloys have been successfully developed by combining Zn-Ni electrodeposition and chemical dealloying techniques. The investigation was focused on elucidating the link between various electrodeposition parameters and the elemental composition, as well as the content of Zn-Ni alloy coatings, both pre-and post-dealloying treatment. This systematic study analysed the effects on composition using Energy Dispersive Spectroscopy (EDS). A water contact angle measurement instrument was employed to assess the wettability of the coated surfaces, yielding detailed data on their hydrophobic characteristics. Moreover, the surface micromorphologies of typical coatings were analysed through Scanning Electron Microscopy (SEM), offering detailed visual insights into the micro- and nano-scale structures. The phase compositions of these coatings are examined using XRD, supplying vital information about the crystalline structures that are in existence. The corrosion prevention function of the superhydrophobic coatings were measured using potentiodynamic polarisation tests. Such tests provide data concerning the durability of the coatings to corrosion in different environments. In this respect, the SCA of the prepared SH sample is reported to be 153.7 ± 1°, which indicates a high degree of hydrophobicity. Additionally, it is claimed that these coatings have excellent chemical stability, excellent adhesion, and good corrosion protection, which makes them highly efficient in protecting surface areas of the AZ91 Mg alloy.

The crosstalk of monocyte-neutrophil in hair follicles regulates neutrophil transepidermal migration in contact dermatitis

The excessive accumulation of neutrophils within the epidermis is a significant hallmark of cutaneous diseases; however, the mechanisms governing neutrophil transepidermal migration (NTEM) remain inadequately understood. In this study, we develop trichromatic-fluorescence-labeled chimeric mice by utilizing Cx3cr1GFP/+Lyz2RFP/+ mice as bone marrow donors and Krt14YFP/+ mice as recipients. This approach enables us to visualize the process of NTEM and the crosstalk between neutrophils and monocytes in a murine model of irritant contact dermatitis (ICD). Intravital imaging reveals a preferential transmigration of neutrophils through hair follicle (HF), where dermal neutrophils exhibit limited mobility and interact with dermal monocytes. Notably, 18 h following hapten exposure, dermal neutrophils continuously migrate toward HF regions and form clusters within 3 h. Importantly, MMP-9 is identified as essential for the NTEM process; the depletion of dermal monocytes results in a significant reduction of MMP-9 expression in the skin and inhibits the NTEM process in ICD. Mechanistically, dermal monocytes are found to be a crucial source of the cytokines TNF-α and CXCL2, which promote the upregulation of MMP-9 in neutrophils. Therefore, our results highlight HF regions as crucial gateways for dermal monocyte-modulated NTEM and provide visual insights into the crosstalk between neutrophils and monocytes in inflammatory skin disorders.

Enhancing people’s walking preferences in street design through generative artificial intelligence and crowdsourcing surveys: The case of Tokyo

The emerging generative artificial intelligence (generative AI) model, Stable Diffusion, is increasingly recognized as a promising tool for efficiently translating public preferences and ideas into spatial design representations. At the same time, deep learning techniques and crowdsourcing methods have enabled the large-scale collection of public walking preference data. This study introduces an innovative approach that leverages the Stable Diffusion model, combined with extensive public walking preference data, to create a workflow for generating revitalized street scenes aimed at enhancing subjective walking preferences. Compared to existing GAN-based methods, the approach used in this study is more efficient to train and generates more realistic and controllable outputs. The approach was tested and validated using data from Tokyo’s Setagaya ward, confirming its effectiveness. This workflow represents a significant advancement in street design and redevelopment, delivering practical value and innovation by equipping designers and planners with rapid visual insights in the early design stages. Additionally, it fosters democratic urban design by utilizing crowdsourced data as training input for generative AI models.

Automatic Active Contour Algorithm for Detecting Early Brain Tumors in Comparison with AI Detection

The automatic detection of objects in medical photographs is an essential component of the diagnostic procedure. The issue of early-stage brain tumor detection has progressed significantly with the use of deep learning algorithms (DLA), particularly convolutional neural networks (CNN). The issue lies in the fact that these algorithms necessitate a training phase involving a large database over several hundred images, which can be time-consuming and require complex computational infrastructure. This study aimed to comprehensively evaluate a proposed method, which relies on an active contour algorithm, for identifying and distinguishing brain tumors in magnetic resonance images. We tested the proposed algorithm using 50 brain images, specifically focusing on glioma tumors, while 2000 images were used for DLA from the BRATS Challenges 2021. The proposed segmentation method is made up of an active contour algorithm, an anisotropic diffusion filter for pre-processing, active contour segmentation (Chan-Vese), and morphologic operations for segmentation refinement. We evaluated its performance using various metrics, such as accuracy, precision, sensitivity, specificity, Jaccard index, Dice index, and Hausdorff distance. The proposed method provided an average of the first six performance metrics of 0.96, which is higher than most classical image segmentation methods and was comparable to the deep learning methods, which have an average performance score of 0.98. These results indicate its ability to detect brain tumors accurately and rapidly. The results section provided both numerical and visual insights into the similarity between segmented and ground truth tumor areas. The findings of this study highlighted the potential of computer-based methods in improving brain tumor identification using magnetic resonance imaging. Future work must validate the efficacy of these segmentation approaches across different brain tumor categories and improve computing efficiency to integrate the technology into clinical processes.

An Automated Repository for the Efficient Management of Complex Documentation

The accelerating digitalization of the public and private sectors has made information technologies (IT) indispensable in modern life. As services shift to digital platforms and technologies expand across industries, the complexity of legal, regulatory, and technical requirement documentation is growing rapidly. This increase presents significant challenges in managing, gathering, and analyzing documents, as their dispersion across various repositories and formats hinders accessibility and efficient processing. This paper presents the development of an automated repository designed to streamline the collection, classification, and analysis of cybersecurity-related documents. By harnessing the capabilities of natural language processing (NLP) models—specifically Generative Pre-Trained Transformer (GPT) technologies—the system automates text ingestion, extraction, and summarization, providing users with visual tools and organized insights into large volumes of data. The repository facilitates the efficient management of evolving cybersecurity documentation, addressing issues of accessibility, complexity, and time constraints. This paper explores the potential applications of NLP in cybersecurity documentation management and highlights the advantages of integrating automated repositories equipped with visualization and search tools. By focusing on legal documents and technical guidelines from Portugal and the European Union (EU), this applied research seeks to enhance cybersecurity governance, streamline document retrieval, and deliver actionable insights to professionals. Ultimately, the goal is to develop a scalable, adaptable platform capable of extending beyond cybersecurity to serve other industries that rely on the effective management of complex documentation.

Visual insights into personalizing women's running shoes: A consumer psychology perspective.

Visual insights into personalizing women's running shoes: A consumer psychology perspective.

Transforming Manufacturing Quality Management with Cognitive Twins: A Data-Driven, Predictive Approach to Real-Time Optimization of Quality

In the ever-changing world of modern manufacturing, maintaining product quality is of great importance, yet extremely difficult due to complexities and the dynamic production paradigm. Currently, quality is rather reactively measured through periodic inspections and manual assessments. Traditional quality management systems (QMS), through these reactive measures, are often inefficient because of their higher operational cost and delayed defect detection and mitigation. The paper introduces a novel cognitive twin (CT) framework, which is the next evolved version of digital twin (DT). It is designed to advance the current quality management in flexible manufacturing systems (FMSs) through real-time, data-driven, and predictive optimization. This proposed framework uses four data types, namely feedstock quality (Qf), machine degradation (Qm), product processing quality (Qp), and quality inspection (Qi). By utilizing the power of machine learning algorithms, the cognitive twin constantly monitors and then analyzes real-time data. The cognitive twin optimizes the above quality components. This enables a very proactive decision making through an augmented reality (AR) interface by providing real-time visual insights and alerts to the operators. Thorough experimentation was conducted on the aforementioned FMS. Through the experiments, it was revealed that the proposed cognitive twin outperforms conventional QMSs by a great margin. The cognitive twin achieved a 2% improvement in the total quality scores. A 60% decrease in defects per unit (DPU) is observed as well as a sharp 40% decrease in scrap rate. Furthermore, the overall equipment efficiency (OEE) increased to 93–96%. The overall equipment efficiency increased by 11.8%, on average, from 82% to 93%, and the scrap rate decreased by 33.3% from 60% to 40%. The excellent results showcase the effectiveness of cognitive twin quality management via minimum wastage, continuous quality improvement, and enhancement in operational efficiency in the paradigm of smart manufacturing. This research study contributes to the field of industry 4.0 by providing a comprehensive, scalable, and adaptive quality management solution, thus leading the way for further advancements in intelligent manufacturing systems.

How to select third-party library: harnessing visual insights and systematic evaluation for informed decisions

The subject of this study is a selection approach for third-party libraries in IT projects based on the collection and analysis of expert evaluations and solving optimization problems. The aim of this study is to minimize the key challenges associated with migrating third-party libraries, including high labor intensity and significant risks that could adversely affect project success. This study sets out several objectives: 1) to create a metric specification to guide evaluation data collection through a survey, focusing on technical metrics. Also, it needs to include recommendations for surveys development; 2) formalize a two-step method that enriches the outcomes and allows for their combined use, where the first step employs radial diagrams to visualize and simplify alternative assessments, and the second step applies the TOPSIS method to address the multi-criteria decision-making problem of selecting a third-party library; 3) the practical application of the proposed approach through illustrative samples. Results. The proposed metrics specification considers the essential technical metrics and offers a unified evaluation solution. We do not limit our approach to technical metrics or numeric data. It is both possible and recommended to include human and economic metrics and to use alternatives to numeric data. The combination of multi-criteria analysis and visual methodologies simplifies the assessment and comparison of libraries, making this approach valuable for developers in practical scenarios. The conclusions of this study emphasize that its findings may lay the groundwork for developing comprehensive decision-support systems focused on third-party library selection, thereby minimizing associated risks. Future developments will include the incorporation of other metrics for library selection, as well as consideration of uncertainty and data subjectivity.