Dimensionality Reduction is a technique used in machine learning to reduce the number of input variables in a dataset, while preserving the essential features. It can help improve the performance of models, reduce overfitting, and decrease computational cost. Techniques include Principal Component Analysis (PCA), t-SNE, and autoencoders.
The RefCap model pioneers visual-linguistic multi-modality in image captioning, incorporating user-specified object keywords. Comprising Visual Grounding, Referent Object Selection, and Image Captioning modules, the model demonstrates efficacy in producing tailored captions aligned with users' specific interests, validated across datasets like RefCOCO and COCO captioning.
Researchers emphasize the growing significance of radar-based human activity recognition (HAR) in safety and surveillance, highlighting its advantages over vision-based sensing in challenging conditions. The study reviews classical Machine Learning (ML) and Deep Learning (DL) approaches, with DL's advantage in avoiding manual feature extraction and ML's robust empirical basis. A comparative study on benchmark datasets evaluates performance and computational efficiency, aiming to establish a standardized assessment framework for radar-based HAR techniques.
This article explores the algorithmic foundations and applications of autoencoders in molecular informatics and drug discovery, with a focus on their role in data-driven molecular representation and constructive molecular design. The study highlights the versatility of autoencoders, especially variational autoencoders (VAEs), in handling diverse molecular data types and their applications in tasks such as dimensionality reduction, preprocessing, and generative molecular design.
This paper introduces an innovative void size extraction algorithm for pavement safety assessments. Leveraging the continuous wavelet transform (CWT) method and ground-penetrating radar (GPR) signals, the algorithm effectively visualizes and accurately measures geometric parameters within void areas.
Researchers introduce a novel approach called Quality Diversity through Human Feedback (QDHF), which leverages human judgments to derive diversity metrics in Quality Diversity (QD) algorithms. This method, based on latent space projection and contrastive learning, offers a more adaptable and effective way to measure diversity, particularly in complex and abstract domains.
This review explores the applications of artificial intelligence (AI) in studying fishing fleet (FV) behavior, emphasizing the role of AI in monitoring and managing fisheries. The paper discusses data sources for FV behavior research, AI techniques used in monitoring FV behavior, and the uses of AI in identifying vessel types, forecasting fishery resources, and analyzing fishing density.
This article delves into the use of deep convolutional neural networks (DCNN) to detect and differentiate synthetic cannabinoids based on attenuated total reflectance Fourier-transform infrared (ATR-FTIR) spectra. The study demonstrates the effectiveness of DCNN models, including a vision transformer-based approach, in classifying and distinguishing synthetic cannabinoids, offering promising applications for drug identification and beyond.
Researchers in China have developed an advanced prediction model, IGWO-SVM, utilizing Grey Wolf Optimization and support vector machines to improve the accuracy of coal and gas outburst predictions in coal mines. This method, along with Random Forest for dimension reduction, holds promise for safer underground mining operations in China's coal industry.
ZairaChem, a groundbreaking AI and machine learning tool, is transforming drug discovery in resource-limited settings. This fully automated framework for quantitative structure-activity relationship (QSAR) and quantitative structure-property relationship (QSPR) modeling accelerates the identification of lead compounds and offers a promising solution for efficient drug discovery.
Researchers delve into the realm of surface electromyography (sEMG), an emerging technology with promising applications in muscle-controlled robots through human-machine interfaces (HMIs). This study, featured in the journal Applied Sciences, delves into the intricacies of sEMG-based robot control, from signal processing and classification to innovative control strategies.
Researchers present the innovative Cost-sensitive K-Nearest Neighbor using Hyperspectral Imaging (CSKNN) method for accurately identifying diverse wheat seed varieties. By addressing challenges such as noise and limited spatial utilization, CSKNN harnesses the power of hyperspectral imaging, noise reduction, feature extraction, and cost sensitivity, outperforming traditional and deep learning methods.
Researchers explore 11 ML algorithms to accurately estimate the uniaxial compressive strength of nanosilica-reinforced concrete. The study highlights the significance of nanomaterial concentration and type in enhancing concrete mechanics, paving the way for informed design and improved water management practices.
Researchers evaluated various machine learning algorithms to predict sheep body weights, highlighting the effectiveness of models like MARS, BRR, ridge regression, SVM, and gradient boosting for improving animal production decisions, ensuring economic growth and food security. Their study showcases the potential of AI in transforming animal husbandry practices.
Researchers introduce MAiVAR-T, a groundbreaking model that fuses audio and image representations with video to enhance multimodal human action recognition (MHAR). By leveraging the power of transformers, this innovative approach outperforms existing methods, presenting a promising avenue for accurate and nuanced understanding of human actions in various domains.
This study presents a novel approach to identifying typical car-to-powered two-wheelers (PTWs) crash scenarios for autonomous vehicle (AV) safety testing. By utilizing stacked autoencoder methods to extract embedded features from high-dimensional crash data, followed by k-means clustering, six high-risk scenarios are identified. Unlike previous research, this method eliminates manual selection of clustering variables and provides a more detailed scenario description, resulting in more robust and effective AV testing scenarios.
Researchers propose a groundbreaking feature engineering methodology for high-frequency financial data analysis, enabling the extraction and forecasting of intraday trends using artificial intelligence models. The approach utilizes time series segmentation and extreme gradient boosting for multiclass classification, focusing on volatility, duration, and direction.
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.