19200 research outputs found
Sort by
Detecting Fake News in Urdu Language Using Machine Learning, Deep Learning, and Large Language Model-Based Approaches
No full textFake news is false or misleading information that looks like real news and spreads through traditional and social media. It has a big impact on our social lives, especially in politics. In Pakistan, where Urdu is the main language, finding fake news in Urdu is difficult because there are not many effective systems for this. This study aims to solve this problem by creating a detailed process and training models using machine learning, deep learning, and large language models (LLMs). The research uses methods that look at the features of documents and classes to detect fake news in Urdu. Different models were tested, including machine learning models like Naïve Bayes and Support Vector Machine (SVM), as well as deep learning models like Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), which used embedding techniques. The study also used advanced models like BERT and GPT to improve the detection process. These models were first evaluated on the Bend-the-Truth dataset, where CNN achieved an F1 score of 72%, Naïve Bayes scored 78%, and the BERT Transformer achieved the highest F1 score of 79% on Bend the Truth dataset. To further validate the approach, the models were tested on a more diverse dataset, Ax-to-Grind, where both SVM and LSTM achieved an F1 score of 89%, while BERT outperformed them with an F1 score of 93%
Compositional Offering as an Antecedent of Service and Financial Performance: Evidence from Pakistani Retail SMEs
No full textIntegrated solutions, which combine products and services to holistically meet customer needs, have been largely overlooked within the context of resource-based theories. Additionally, developing such solutions from a service-dominant logic perspective remains under-researched. This study addresses these gaps by utilizing composition-based theory as its theoretical lens to investigate the impact of compositional offerings on service and financial performance within Pakistani retail stores. A survey of 120 small and medium retail stores, analyzed using structural equation modelling, reveals a positive association between a firm’s compositional offerings and its service and financial performance outcomes. Furthermore, service performance mediates the relationship between compositional offerings and financial performance. The findings have significant implications for managers, who can use compositional offerings to enhance the service and financial performances of their businesses. Thus, compositional offering boosts financial performance by improving customer satisfaction, retention and brand image
<scp>Karen Hellman</scp> and <scp>Carolyn Peter</scp> , <i>Hippolyte Bayard and the Invention of Photography</i>
No full text
An operator-based service orchestration method formedical image intelligent analysis systems
No full textMedical image intelligent analysis systems using deep learning models for lesion segmentation in medical images, such asX-ray, CT, MRI, and ultrasound could assist doctors to improve the efficiency of clinic diagnosis and treatment, especiallyin the early diagnosis of diseases such as pulmonary fibrosis. The challenge for quick response of lesion segmentation underenvironment of a large number of patient visits is that AI models need to handle a large number of inference computation,for instance, a set of lung CT scan of a patient usually contains more than 300 images. This paper proposes a serviceorchestration method, aiming to address the above challenge by improving the parallelization of the process of AI modelinference at a smaller granularity which is called as operator. The proposed operator-based method includes phases of AImodel operarization, operator instance composition, and operator dynamic scheduling. Firstly, complex deep learning modelsare decomposed into independent operators. Then, operator instances are combined to form the whole inference process ofan AI model in a Directed Acyclic Graph (DAG) structure. Finally, considering both the logical dependency implied in theDAG and the computational resources required for operator execution, a scheduling algorithm is designed to automaticallyparallelize the whole process of lesion segmentation. The feasibility of the method is validated through a case study of apulmonary fibrosis diagnostic suppo
Advancing Cybersecurity in Smart Factories Through Autonomous Robotic Defenses
No full textAdvancing Cybersecurity in Smart Factories Through Autonomous Robotic Defenses bridges the gap between the technical aspects of AI, industrial automation, and the evolving landscape of cybersecurity. This book provides readers with insight into the most recent advancements in AI-powered security tools, explore ethical and regulatory considerations, and learn practical strategies to protect complex systems from cyberattacks. Covering topics such as smart factories, wearable devices, and drone systems, this book is an excellent resource for cybersecurity professionals, computer engineers, industrial engineers, policymakers, policy regulators, professionals, researchers, scholars, academicians, and more
Sugar Intake Is Associated With Increased Odds of Depression and Anxiety: Evidence From A Cross‐Sectional Study
Get PDFBackground and Aims: The current study aimed to assess the associations between (i) total and specific sugar intake, (ii) dietary exposures that met Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) selection criteria for risk factors, and depression and anxiety. Methods: In this online cross‐sectional study that took place between 2022 and 2024 in the United Kingdom, 377 participants between the ages of 18–66 years (M = 26.09; SD = 8.48) completed the: EPIC‐Norfolk Food Frequency Questionnaire from which overall sugar intake, specific sugar intake (fructose, galactose, glucose, lactose, maltose, and sucrose) and GBD dietary exposures were derived; and the Depression, Anxiety and Stress Scales from which likely depression and anxiety cases were identified. Results: The prevalence of depression and anxiety was 12.5% and 16.4%, respectively. Separate logistic regression models assessing the associations between dietary intake and depression) and anxiety revealed that total sugar intake was associated with greater odds of depression (OR: 1.01, 95% CI 1.00–1.02) and anxiety (OR: 1.01, 95%CI 1.01–1.02). Specifically, higher sucrose intake was associated with greater odds of anxiety (OR: 1.02, 95%CI 1.00–1.05), while higher intake of sugar‐sweetened beverages was associated with increased odds of both depression (OR: 1.00, 95%CI 1.00–1.01) and anxiety (OR: 1.00, 95%CI 1.00–1.01). Conclusion: While higher overall sugar intake was associated with both depression and anxiety, sucrose intake emerged as a specific factor associated with increased odds of anxiety, and higher sugar‐sweetened beverages intake with depression and anxiety, warranting further investigation into their potential role in mental health outcomes
