A neural network is a computational model inspired by the structure and function of the human brain. It consists of interconnected artificial neurons that process and transmit information, enabling machine learning tasks such as pattern recognition, classification, and regression by learning from labeled data.
Researchers devise interpretable and non-interpretable ML models optimized by particle swarm optimization to accurately estimate crop evapotranspiration for winter wheat. By utilizing limited meteorological data, these models offer insights into water usage and agricultural sustainability, aiding water management practices in the face of climate challenges.
Researchers introduce a revolutionary method combining Low-Level Feature Attention, Feature Fusion Neck, and Context-Spatial Decoupling Head to enhance object detection in dim environments. With improvements in accuracy and real-world performance, this approach holds promise for applications like nighttime surveillance and autonomous driving.
Researchers delve into the realm of Citizen-Centric Digital Twins (CCDT), exploring cutting-edge technologies that enable predictive, simulative, and visualizing capabilities to address city-level issues through citizen engagement. The study highlights data acquisition methods, machine learning algorithms, and APIs, offering insights into enhancing urban management while fostering public participation.
Researchers introduce the Gap Layer modified Convolution Neural Network (GL-CNN) coupled with IoT and Unmanned Aerial Vehicles (UAVs) for accurate and efficient monitoring of palm tree seedling growth. This approach utilizes advanced image analysis techniques to predict seedling health, addressing challenges in early-stage plant monitoring and restoration efforts. The GL-CNN architecture achieves impressive accuracy, highlighting its potential for transforming ecological monitoring in smart farming.
This article delves into the transformational potential of automated driving (AD) systems on transportation, focusing on the integration of prediction and planning. While traditionally treated as separate tasks, recent insights advocate for an integrated approach to anticipate responses of other traffic participants. The review extensively covers cutting-edge deep learning models for prediction, planning, and their integration, highlighting strengths, limitations, and implications.
Researchers delve into AI's role in carbon reduction in buildings, discussing energy prediction, ML-driven emission mitigation, and carbon accounting. The paper underscores urgent emission reduction in construction, highlighting ML's potential to drive sustainable practices, with a focus on AI's positive impact on the low-carbon building sector.
Researchers have introduced a transformative approach utilizing deep reinforcement learning (DRL) and a transformer-based policy network to optimize energy-efficient routes for electric logistic vehicles. By addressing the Energy-Minimization Electric Vehicle Routing Problem (EM-EVRP), this study aimed to reduce operating expenses for electric fleets while accommodating factors like vehicle dynamics, road features, and charging losses.
Researchers introduce a novel approach using TinyML sensors and models to estimate the shelf life of fresh dates non-destructively. The study develops a lightweight TinyML system combining a miniature NIR spectral sensor and an Arduino microcontroller for on-device inference. This edge computing approach enables real-time prediction of date shelf life, eliminating the need for continuous cloud connectivity.
The paper delves into recent advancements in facial emotion recognition (FER) through neural networks, highlighting the prominence of convolutional neural networks (CNNs), and addressing challenges like authenticity and diversity in datasets, with a focus on integrating emotional intelligence into AI systems for improved human interaction.
Researchers present an innovative framework that integrates voice and gesture commands through multimodal fusion, enabling effective and secure communication between humans and robots. This architecture, combined with a safety layer, ensures both natural interaction and compliance with safety measures, showcasing its potential through a comparative experiment in pick-and-place tasks.
Researchers introduce an innovative AI model that outperforms existing methods in Parkinson's disease (PD) detection. Leveraging a transformer-based architecture and neural network, this model utilizes vocal features to achieve superior accuracy, providing potential for early intervention in PD cases.
This study presents an innovative pipeline for continuous real-time assessment of driver drowsiness levels using photoplethysmography (PPG) signals. The approach involves customized PPG sensors embedded in the steering wheel, coupled with a tailored deep neural network architecture for accurate drowsiness classification. Previous methods using ECG signals were susceptible to motion artifacts and complex preprocessing.
Researchers introduce an innovative solution for intelligent identification of natural gas pipeline defects. By enhancing the Flower Pollination Algorithm (FPA) with adaptive adjustments and Gaussian mutation, the Improved Flower Pollination Algorithm (IFPA) optimizes input weights for the Extreme Learning Machine (ELM). IFPA-ELM achieves impressive defect recognition rates of 97% and 96%, surpassing benchmarks and showcasing potential for advanced pipeline defect diagnosis.
Researchers introduce ILNet, an image-loop neural network (ILNet) that marries deep learning with single-pixel imaging (SPI), leading to high-quality image reconstruction at remarkably low sampling rates. By incorporating a part-based model and iterative optimization, ILNet outperforms traditional methods in both free-space and underwater scenarios, offering a breakthrough solution for imaging in challenging environments.
This cutting-edge research explores a novel deep learning approach for network intrusion detection using a smaller feature vector. Achieving higher accuracy and reduced computational complexity, this method offers significant advancements in cybersecurity defense against evolving threats.
The DCTN model, combining deep convolutional neural networks and Transformers, demonstrates superior accuracy in hydrologic forecasting and climate change impact evaluation, outperforming traditional models by approximately 30.9%. The model accurately predicts runoff patterns, aiding in water resource management and climate change response.
Researchers present a novel framework for fault diagnosis of electrical motors using self-supervised learning and fine-tuning on a neural network-based backbone. The proposed model achieves high-performance fault diagnosis with minimal labeled data, addressing the limitations of traditional approaches and demonstrating scalability, expressivity, and generalizability for diverse fault diagnosis tasks.
Researchers introduce FERN, a neural encoder-decoder model designed to revolutionize earthquake rate forecasting. By overcoming the limitations of traditional models like ETAS, FERN leverages the power of artificial intelligence and deep learning algorithms to provide more accurate and flexible earthquake predictions. With its ability to incorporate diverse geophysical data and offer improved short-term forecasts, FERN holds promise for enhancing seismic risk management and ensuring safer communities in earthquake-prone regions.
This research paper introduces a novel approach using supervised hybrid quantum machine learning to improve emergency evacuation strategies for cars during natural disasters like earthquakes. The proposed method combines quantum and classical machine learning techniques, demonstrating superior accuracy and efficiency compared to conventional algorithms, and holds promise for real-world applications in dynamic environments.
Researchers propose the Fine-Tuned Channel-Spatial Attention Transformer (FT-CSAT) model to address challenges in facial expression recognition (FER), such as facial occlusion and head pose changes. The model combines the CSWin Transformer with a channel-spatial attention module and fine-tuning techniques to achieve state-of-the-art accuracy on benchmark datasets, showcasing its robustness in handling FER challenges.
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.