Machine learning is a subfield of artificial intelligence that focuses on developing algorithms and models capable of automatically learning and making predictions or decisions from data without being explicitly programmed. It involves training models on labeled datasets to recognize patterns and make accurate predictions or classifications in new, unseen data.
This study explores the development and usability of the AIIS (Artificial Intelligence, Innovation, and Society) collaborative learning interface, a metaverse-based educational platform designed for undergraduate students. The research demonstrates the potential of immersive technology in education and offers insights and recommendations for enhancing metaverse-based learning systems.
This research paper introduces innovative machine learning techniques, including Artificial Neural Networks (ANN) and Support Vector Machines (SVM), to assess critical speeds on railway tracks, especially those on soft soils. The study's dataset, created through advanced numerical methods and validated experiments, supports the development of predictive models for assessing critical speeds in various track sections.
Researchers have introduced a lightweight yet efficient safety helmet detection model, SHDet, based on the YOLOv5 architecture. This model optimizes the YOLOv5 backbone, incorporates upsampling and attention mechanisms, and achieves impressive performance with faster inference speeds, making it a promising solution for real-world applications on construction sites.
Researchers have harnessed the power of Vision Transformers (ViT) to revolutionize fashion image classification and recommendation systems. Their ViT-based models outperformed CNN and pre-trained models, achieving impressive accuracy in classifying fashion images and providing efficient and accurate recommendations, showcasing the potential of ViTs in the fashion industry.
This research paper explores the impact of various factor screening methods on predictive modeling accuracy for landslide susceptibility mapping. Using 2014 landslide data from Jingdong County, the study employs factor screening techniques and a random forest model to improve prediction accuracy, with the Information Gain Ratio (IGR) and Random Forest (IGR_RF) model emerging as the most effective approach.
Researchers apply three deep learning models and Bayesian Model Averaging (BMA) to enhance water level predictions at multiple stations around Poyang Lake. Their approach, combining DL models with BMA, demonstrated improved accuracy in forecasting and reduced uncertainty, offering valuable insights for disaster mitigation and resource management in the region.
The use of Artificial Intelligence (AI) in environmental science is on the rise, offering efficient ways to analyze complex data and address ecological concerns. However, the energy consumption and carbon emissions associated with AI models are concerns that need mitigation. Collaboration between environmental and AI experts is essential to maximize AI's potential in addressing environmental challenges while ensuring ethical and sustainable practices.
Researchers deploy advanced techniques, including Artificial Neural Networks (ANN), to accurately forecast Construction Cost Index (CCI) in developing countries, with Pakistan as a case study. The ANN model stands out, providing precise predictions, thereby revolutionizing cost estimation in the construction industry and promoting economic stability.
This article discusses the application of machine learning models to predict anomalies in daily maximum temperatures in India from March to June. The study evaluates various machine learning models and identifies an optimal model, emphasizing its effectiveness in forecasting extreme temperature events, with the potential to complement numerical weather prediction models.
This research paper discusses the application of machine learning (ML) techniques to enhance the reusability of learning objects in e-learning systems. It employs web exploration algorithms, feature selection, and advanced ML algorithms, such as Fuzzy C-Means and Multi-Label Classification, to categorize learning objects and improve their accessibility, ultimately leading to a more personalized and efficient learning experience.
This article discusses research efforts to improve general-purpose pre-trained language models' performance in commonsense reasoning, particularly focusing on the Com2Sense Dataset. The study introduces machine learning-based methods, including knowledge transfer, contrastive loss functions, and ensemble techniques, which significantly enhance model performance, demonstrating potential for improved commonsense reasoning in natural language understanding.
This research paper discusses the application of machine learning algorithms to predict the Water Quality Index (WQI) in groundwater in Sakrand, Pakistan. The study collected data samples, applied various classifiers, and found that the linear Support Vector Machine (SVM) model demonstrated the highest prediction accuracy for both raw and normalized data, with potential applications in assessing groundwater quality for various purposes, including drinking and irrigation.
Researchers present the "SCALE" framework, which evaluates the impact of AI on the mortgage market, with a focus on promoting homeownership inclusivity for marginalized communities. The framework encompasses societal values, contextual integrity, accuracy, legality, and expanded opportunity, aiming to address concerns about bias and discrimination in AI applications within the mortgage industry while advancing fair lending practices and social equity in homeownership.
This paper explores the increasing presence of autonomous artificial intelligence (AI) systems in healthcare and the associated concerns related to liability, regulatory compliance, and financial aspects. It discusses how evolving regulations, such as those from the FDA, aim to ensure transparency and accountability, and how payment models like Medicare Physician Fee Schedule (MPFS) are adapting to accommodate autonomous AI integration.
This article highlights the groundbreaking introduction of CapGAN, a novel model for generating images from textual descriptions. CapGAN leverages capsule networks within an adversarial framework to enhance the modeling of hierarchical relationships among object entities, resulting in the creation of diverse, meaningful, and realistic images.
This research combines Radio-Frequency Identification (RFID) technology and machine learning to analyze customer browsing behaviors in physical retail stores. By using methods like Isolation Forest (iForest) and Adaptive Synthetic Sampling (ADASYN), the model achieved remarkable accuracy and can be integrated into a web-based application, providing valuable insights for store optimization and customer experience enhancement.
This study employs Explainable Artificial Intelligence (XAI) to analyze obesity prevalence across 3,142 U.S. counties. Machine learning models, coupled with interpretability techniques, reveal physical inactivity, diabetes, and smoking as primary contributors to obesity disparities. XAI advances understanding and intervention in obesity-related health challenges.
In a groundbreaking study, AI-driven data analysis accurately predicts Greco-Roman wrestlers' competitive success, with just an 11% error rate. This research has the potential to revolutionize athlete selection and training in various sports, offering valuable insights for coaches and athletes alike.
This research delves into the application of machine learning (ML) algorithms in wastewater treatment, examining their impact on this essential environmental discipline. Through text mining and analysis of scientific literature, the study identifies popular ML models and their relevance, emphasizing the increasing role of ML in addressing complex challenges in wastewater treatment, while also highlighting the importance of data quality and model interpretation.
This research introduces an innovative approach to robot representation learning, emphasizing the importance of human-oriented perceptual skills. By leveraging well-labeled video datasets containing human priors, the study enhances visual-motor control through human-guided fine-tuning and introduces the Task Fusion Decoder, which integrates multiple task-specific information.
Terms
While we only use edited and approved content for Azthena
answers, it may on occasions provide incorrect responses.
Please confirm any data provided with the related suppliers or
authors. We do not provide medical advice, if you search for
medical information you must always consult a medical
professional before acting on any information provided.
Your questions, but not your email details will be shared with
OpenAI and retained for 30 days in accordance with their
privacy principles.
Please do not ask questions that use sensitive or confidential
information.
Read the full Terms & Conditions.