Search Results (17)

Interpreting diagnostic imaging and identifying clinically relevant features remain challenging tasks, particularly for novice radiologists who often lack structured guidance and expert feedback. To bridge this gap, we propose an Eye-Gaze Guided Multimodal Fusion framework that leverages expert eye-tracking data to enhance learning and decision-making in medical image interpretation. By integrating chest X-ray (CXR) images with expert fixation maps, our approach captures radiologists’ visual attention patterns and highlights regions of interest (ROIs) critical for accurate diagnosis. The fusion model utilizes a shared backbone architecture to jointly process image and gaze modalities, thereby minimizing the impact of noise in fixation data. We validate the system’s interpretability using Gradient-weighted Class Activation Mapping (Grad-CAM) and assess both classification performance and explanation alignment with expert annotations. Comprehensive evaluations, including robustness under gaze noise and expert clinical review, demonstrate the framework’s effectiveness in improving model reliability and interpretability. This work offers a promising pathway toward intelligent, human-centered AI systems that support both diagnostic accuracy and medical training. Full article

Customers are the cornerstone of business success across industries. Companies invest significant resources in acquiring new customers and, more importantly, retaining existing ones. However, customer churn remains a major challenge, leading to substantial financial losses. Addressing this issue requires a deep understanding of customers’ cognitive status and behaviours, as well as early signs of churn. Predictive and Machine Learning (ML)-based analysis, when trained with appropriate features indicative of customer behaviour and cognitive status, can be highly effective in mitigating churn. A robust ML-driven churn analysis depends on a well-developed feature engineering process. Traditional churn analysis studies have primarily relied on demographic, product usage, and revenue-based features, overlooking the valuable insights embedded in customer–company interactions. Recognizing the importance of domain knowledge and human expertise in feature engineering and building on our previous work, we propose the Customer Churn-related Knowledge Base (ChurnKB) to enhance feature engineering for churn prediction. ChurnKB utilizes textual data mining techniques such as Term Frequency-Inverse Document Frequency (TF-IDF), cosine similarity, regular expressions, word tokenization, and stemming to identify churn-related features within customer-generated content, including emails. To further enrich the structure of ChurnKB, we integrate Generative AI, specifically large language models, which offer flexibility in handling unstructured text and uncovering latent features, to identify and refine features related to customer cognitive status, emotions, and behaviours. Additionally, feedback loops are incorporated to validate and enhance the effectiveness of ChurnKB.Integrating knowledge-based features into machine learning models (e.g., Random Forest, Logistic Regression, Multilayer Perceptron, and XGBoost) improves predictive performance of ML models compared to the baseline, with XGBoost’s F1 score increasing from 0.5752 to 0.7891. Beyond churn prediction, this approach potentially supports applications like personalized marketing, cyberbullying detection, hate speech identification, and mental health monitoring, demonstrating its broader impact on business intelligence and online safety. Full article

Understanding the regulatory mechanisms of gene expression is a crucial objective in genomics. Although the DNA sequence near the transcription start site (TSS) offers valuable insights, recent methods suggest that analyzing only the surrounding DNA may not suffice to accurately predict gene expression levels. We developed GENet (Gene Expression Network from Histone and Transcription Factor Integration), a novel approach that integrates essential regulatory signals from transcription factors and histone modifications into a graph-based model. GENet extends beyond simple DNA sequence analysis by incorporating additional layers of genetic control, which are vital for determining gene expression. Our method markedly enhances the prediction of mRNA levels compared to previous models that depend solely on DNA sequence data. The results underscore the significance of including comprehensive regulatory information in gene expression studies. GENet emerges as a promising tool for researchers, with potential applications extending from fundamental biological research to the development of medical therapies. Full article

Predicting student outcomes is an essential task and a central challenge among artificial intelligence-based personalised learning applications. Despite several studies exploring student performance prediction, there is a notable lack of comprehensive and comparative research that methodically evaluates and compares multiple machine learning models alongside deep learning architectures. In response, our research provides a comprehensive comparison to evaluate and improve ten different machine learning and deep learning models, either well-established or cutting-edge techniques, namely, random forest, decision tree, support vector machine, K-nearest neighbours classifier, logistic regression, linear regression, and state-of-the-art extreme gradient boosting (XGBoost), as well as a fully connected feed-forward neural network, a convolutional neural network, and a gradient-boosted neural network. We implemented and fine-tuned these models using Python 3.9.5. With a keen emphasis on prediction accuracy and model performance optimisation, we evaluate these methodologies across two benchmark public student datasets. We employ a dual evaluation approach, utilising both k-fold cross-validation and holdout methods, to comprehensively assess the models’ performance. Our research focuses primarily on predicting student outcomes in final examinations by determining their success or failure. Moreover, we explore the importance of feature selection using the ubiquitous Lasso for dimensionality reduction to improve model efficiency, prevent overfitting, and examine its impact on prediction accuracy for each model, both with and without Lasso. This study provides valuable guidance for selecting and deploying predictive models for tabular data classification like student outcome prediction, which seeks to utilise data-driven insights for personalised education. Full article

This study delves into the realm of Explainable Artificial Intelligence (XAI) frameworks, aiming to empower researchers and practitioners with a deeper understanding of these tools. We establish a comprehensive knowledge base by classifying and analyzing prominent XAI solutions based on key attributes like explanation type, model dependence, and use cases. This resource equips users to navigate the diverse XAI landscape and select the most suitable framework for their specific needs. Furthermore, the study proposes a novel framework called XAIE (eXplainable AI Evaluator) for informed decision-making in XAI adoption. This framework empowers users to assess different XAI options based on their application context objectively. This will lead to more responsible AI development by fostering transparency and trust. Finally, the research identifies the limitations and challenges associated with the existing XAI frameworks, paving the way for future advancements. By highlighting these areas, the study guides researchers and developers in enhancing the capabilities of Explainable AI. Full article

This study presents a responsive analysis of the role of artificial intelligence (AI) in risk management, contrasting traditional approaches with those augmented by AI and highlighting the challenges and opportunities that emerge. AI, intense learning methodologies such as convolutional neural networks (CNNs), have been identified as pivotal in extracting meaningful insights from image data, a form of analysis that holds significant potential in identifying and managing risks across various industries. The research methodology involves a strategic selection and processing of images for analysis and introduces three case studies that serve as benchmarks for evaluation. These case studies showcase the application of AI, in place of image processing capabilities, to identify hazards, evaluate risks, and suggest control measures. The comparative evaluation focuses on the accuracy, relevance, and practicality of the AI-generated findings alongside the system’s response time and comprehensive understanding of the context. Results reveal that AI can significantly enhance risk assessment processes, offering rapid and detailed insights. However, the study also recognises the intrinsic limitations of AI in contextual interpretation, advocating for a synergy between technological and domain-specific expertise. The conclusion underscores the transformative potential of AI in risk management, supporting continued research to further integrate AI effectively into risk assessment frameworks. Full article

Numerous studies have established a correlation between creativity and intrinsic motivation to learn, with creativity defined as the process of generating original and valuable ideas, often by integrating perspectives from different fields. The field of educational technology has shown a growing interest in leveraging technology to promote creativity in the classroom, with several studies demonstrating the positive impact of creativity on learning outcomes. However, mining creative thinking patterns from educational data remains a challenging task, even with the proliferation of research on adaptive technology for education. This paper presents an initial effort towards formalizing educational knowledge by developing a domain-specific Knowledge Base that identifies key concepts, facts, and assumptions essential for identifying creativity patterns. Our proposed pipeline involves modeling raw educational data, such as assessments and class activities, as a graph to facilitate the contextualization of knowledge. We then leverage a rule-based approach to enable the mining of creative thinking patterns from the contextualized data and knowledge graph. To validate our approach, we evaluate it on real-world datasets and demonstrate how the proposed pipeline can enable instructors to gain insights into students’ creative thinking patterns from their activities and assessment tasks. Full article

Instructors face significant time and effort constraints when grading students’ assessments on a large scale. Clustering similar assessments is a unique and effective technique that has the potential to significantly reduce the workload of instructors in online and large-scale learning environments. By grouping together similar assessments, marking one assessment in a cluster can be scaled to other similar assessments, allowing for a more efficient and streamlined grading process. To address this issue, this paper focuses on text assessments and proposes a method for reducing the workload of instructors by clustering similar assessments. The proposed method involves the use of distributed representation to transform texts into vectors, and contrastive learning to improve the representation that distinguishes the differences among similar texts. The paper presents a general framework for clustering similar texts that includes label representation, K-means, and self-organization map algorithms, with the objective of improving clustering performance using Accuracy (ACC) and Normalized Mutual Information (NMI) metrics. The proposed framework is evaluated experimentally using two real datasets. The results show that self-organization maps and K-means algorithms with Pre-trained language models outperform label representation algorithms for different datasets. Full article

The widespread adoption of advanced technologies, such as Artificial Intelligence (AI), Machine Learning, and Robotics, is rapidly increasing across the globe. This accelerated pace of change is drastically transforming various aspects of our lives and work, resulting in what is now known as Industry 4.0. As businesses integrate these technologies into their daily operations, it significantly impacts their work tasks and required skill sets. However, the approach to technological transformation varies depending on location, industry, and organization. However, there are no published methods that can adequately forecast the adoption of technology and its impact on society. It is essential to prepare for the future impact of Industry 4.0, and this requires policymakers and business leaders to be equipped with scientifically validated models and metrics. Data-driven scenario planning and decision-making can lead to better outcomes in every area of the business, from learning and development to technology investment. However, the current literature falls short in identifying effective and globally applicable strategies to predict the adoption rate of emerging technologies. Therefore, this paper proposes a novel parametric mathematical model for predicting the adoption rate of emerging technologies through a unique data-driven pipeline. This approach utilizes global indicators for countries to predict the technology adoption curves for each country and industry. The model is thoroughly validated, and the paper outlines highly promising evaluation results. The practical implications of this proposed approach are significant because it provides policymakers and business leaders with valuable insights for decision-making and scenario planning. Full article

In our digital age, data are generated constantly from public and private sources, social media platforms, and the Internet of Things. A significant portion of this information comes in the form of unstructured images and videos, such as the 95 million daily photos and videos shared on Instagram and the 136 billion images available on Google Images. Despite advances in image processing and analytics, the current state of the art lacks effective methods for discovering, linking, and comprehending image data. Consider, for instance, the images from a crime scene that hold critical information for a police investigation. Currently, no system can interactively generate a comprehensive narrative of events from the incident to the conclusion of the investigation. To address this gap in research, we have conducted a thorough systematic literature review of existing methods, from labeling and captioning to extraction, enrichment, and transforming image data into contextualized information and knowledge. Our review has led us to propose the vision of storytelling with image data, an innovative framework designed to address fundamental challenges in image data comprehension. In particular, we focus on the research problem of understanding image data in general and, specifically, curating, summarizing, linking, and presenting large amounts of image data in a digestible manner to users. In this context, storytelling serves as an appropriate metaphor, as it can capture and depict the narratives and insights locked within the relationships among data stored across different islands. Additionally, a story can be subjective and told from various perspectives, ranging from a highly abstract narrative to a highly detailed one. Full article

Prostate cancer (PC) is the most frequently diagnosed non-skin cancer in the world. Previous studies have shown that genomic alterations represent the most common mechanism for molecular alterations responsible for the development and progression of PC. This highlights the importance of identifying functional genomic variants for early detection in high-risk PC individuals. Great efforts have been made to identify common protein-coding genetic variations; however, the impact of non-coding variations, including regulatory genetic variants, is not well understood. Identification of these variants and the underlying target genes will be a key step in improving the detection and treatment of PC. To gain an understanding of the functional impact of genetic variants, and in particular, regulatory variants in PC, we developed an integrative pipeline (AGV) that uses whole genome/exome sequences, GWAS SNPs, chromosome conformation capture data, and ChIP-Seq signals to investigate the potential impact of genomic variants on the underlying target genes in PC. We identified 646 putative regulatory variants, of which 30 significantly altered the expression of at least one protein-coding gene. Our analysis of chromatin interactions data (Hi-C) revealed that the 30 putative regulatory variants could affect 131 coding and non-coding genes. Interestingly, our study identified the 131 protein-coding genes that are involved in disease-related pathways, including Reactome and MSigDB, for most of which targeted treatment options are currently available. Notably, our analysis revealed several non-coding RNAs, including RP11-136K7.2 and RAMP2-AS1, as potential enhancer elements of the protein-coding genes CDH12 and EZH1, respectively. Our results provide a comprehensive map of genomic variants in PC and reveal their potential contribution to prostate cancer progression and development. Full article

Here we developed KARAJ, a fast and flexible Linux command-line tool to automate the end-to-end process of querying and downloading a wide range of genomic and transcriptomic sequence data types. The input to KARAJ is a list of PMCIDs or publication URLs or various types of accession numbers to automate four tasks as follows; firstly, it provides a summary list of accessible datasets generated by or used in these scientific articles, enabling users to select appropriate datasets; secondly, KARAJ calculates the size of files that users want to download and confirms the availability of adequate space on the local disk; thirdly, it generates a metadata table containing sample information and the experimental design of the corresponding study; and lastly, it enables users to download supplementary data tables attached to publications. Further, KARAJ provides a parallel downloading framework powered by Aspera connect which reduces the downloading time significantly. Full article

In blockchain technology, all registered information, from the place of production of the product to its point of sale, is recorded as permanent and unchangeable, and no intermediary has the ability to change the data of other members and even the data registered by them without public consensus. In this way, users can trust the accuracy of the data. Blockchain systems have a wide range of applications in the medical and health sectors, from creating an integrated system for recording and tracking patients’ medical records to creating transparency in the drug supply chain and medical supplies. However, implementing blockchain technology in the supply chain has limitations and sometimes has risks. In this study, BWM methods and VIKORSort have been used to classify the risks of implementing blockchain in the drug supply chain. The results show that cyberattacks, double spending, and immutability are very dangerous risks for implementation of blockchain technology in the drug supply chain. Therefore, the risks of blockchain technology implementation in the drug supply chain have been classified based on a literature review and opinions of the experts. The risks of blockchain technology implementation in the supply chain were determined from the literature review. Full article

It is now known that at least 10% of samples with pancreatic cancers (PC) contain a causative mutation in the known susceptibility genes, suggesting the importance of identifying cancer-associated genes that carry the causative mutations in high-risk individuals for early detection of PC. In this study, we develop a statistical pipeline using a new concept, called gene-motif, that utilizes both mutated genes and mutational processes to identify 4211 3-nucleotide PC-associated gene-motifs within 203 significantly mutated genes in PC. Using these gene-motifs as distinguishable features for pancreatic cancer subtyping results in identifying five PC subtypes with distinguishable phenotypes and genotypes. Our comprehensive biological characterization reveals that these PC subtypes are associated with different molecular mechanisms including unique cancer related signaling pathways, in which for most of the subtypes targeted treatment options are currently available. Some of the pathways we identified in all five PC subtypes, including cell cycle and the Axon guidance pathway are frequently seen and mutated in cancer. We also identified Protein kinase C, EGFR (epidermal growth factor receptor) signaling pathway and P53 signaling pathways as potential targets for treatment of the PC subtypes. Altogether, our results uncover the importance of considering both the mutation type and mutated genes in the identification of cancer subtypes and biomarkers. Full article

Bioinformatics and computational biology have significantly contributed to the generation of vast and important knowledge that can lead to great improvements and advancements in biology and its related fields. Over the past three decades, a wide range of tools and methods have been developed and proposed to enhance performance, diagnosis, and throughput while maintaining feasibility and convenience for users. Here, we propose a new user-friendly comprehensive tool called VIRMOTIF to analyze DNA sequences. VIRMOTIF brings different tools together as one package so that users can perform their analysis as a whole and in one place. VIRMOTIF is able to complete different tasks, including computing the number or probability of motifs appearing in DNA sequences, visualizing data using the matplotlib and heatmap libraries, and clustering data using four different methods, namely K-means, PCA, Mean Shift, and ClusterMap. VIRMOTIF is the only tool with the ability to analyze genomic motifs based on their frequency and representation (D-ratio) in a virus genome. Full article