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.
This groundbreaking study introduces a deep learning (DL)-based approach for Label-Free Identification of Neurodegenerative Disease (NDD)-associated Aggregates (LINA). Addressing limitations of fluorescently tagged proteins, the method accurately identifies unaltered and unlabeled protein aggregates in living cells, focusing on Huntington's disease (HD) as a model.
This paper introduces FollowNet, a pioneering initiative addressing challenges in modeling car-following behavior. With a unified benchmark dataset consolidating over 80K car-following events from diverse public driving datasets, FollowNet sets a standard for evaluating and comparing car-following models, overcoming format inconsistencies in existing datasets.
Researchers present an intelligent framework, integrating a Group Method of Data Handling (GMDH) neural network and Shapley Additive Explanations (SHAP) analysis, to predict free atmospheric corrosion in marine steel structures. Leveraging historical sensor data, the framework demonstrates high forecasting accuracy, with optimal parameter selection enhancing performance. The SHAP analysis reveals the impact of environmental factors on corrosion, providing valuable insights into the dynamics of atmospheric corrosion in marine settings.
The paper provides a comprehensive review of artificial intelligence (AI)-assisted wireless localization technologies addressing limitations in existing systems. It discusses AI algorithms to counteract signal quality deterioration, spatiotemporal asynchronization, non-line-of-sight (NLoS) event identification, and miscellaneous methods for performance enhancement.
Researchers introduced an innovative method for real-time table tennis ball landing point determination, minimizing reliance on complex visual equipment. The approach, incorporating dynamic color thresholding, target area filtering, keyframe extraction, and advanced detection algorithms, significantly improved processing speed and accuracy. Tested on the Jetson Nano development board, the method showcased exceptional performance.
Researchers presented a traffic-predicting model, utilizing deep learning techniques, to identify and prevent congestion from large flow sizes (elephant flows) in software-defined networks (SDN). The model, evaluated with an SDN dataset, demonstrated high accuracy in distinguishing elephant flows, and the SHapley Additive exPlanations (SHAP) technique provided detailed insights into feature importance, contributing to potential applications in real-time adaptive traffic management for improved Quality of Service (QoS) in various domains.
This study unveils a groundbreaking dataset of over 1.3 million solar magnetogram images paired with solar flare records. Spanning two solar cycles, the dataset from NASA's Solar Dynamics Observatory facilitates advanced studies in solar physics and space weather prediction. The innovative approach, integrating multi-source information and applying machine learning models, showcases the dataset's potential for improving our understanding of solar phenomena and paving the way for highly accurate automated solar flare forecasting systems.
This research delves into the realm of electronic board manufacturing, aiming to enhance reliability and lifespan through the automated detection of solder splashes using cutting-edge machine learning algorithms. The study meticulously compares object detection models, emphasizing the efficacy of the custom-trained YOLOv8n model with 1.9 million parameters, showcasing a rapid 90 ms detection speed and an impressive mean average precision of 96.6%. The findings underscore the potential for increased efficiency and cost savings in electronic board manufacturing, marking a significant shift from manual inspection to advanced machine learning techniques.
Researchers present an innovative approach to dyslexia identification using a multi-source dataset incorporating eye movement, demographic, and non-verbal intelligence data. Experimenting with various AI models, including MLP, RF, GB, and KNN, the study demonstrates the efficacy of a fusion of demographic and fixation data in accurate dyslexia prediction. The insights gained, including the significance of IQ, age, and gender, pave the way for enhanced dyslexia detection, while challenges like data imbalance prompt considerations for future improvements.
This paper presents a groundbreaking approach to tackle beam management challenges in vehicle-to-vehicle (V2V) communication. Leveraging a deep reinforcement learning (DRL) framework, specifically the Iterative Twin Delayed Deep Deterministic (ITD3) model with Gated Recurrent Unit (GRU), the study significantly improves spectral efficiency and reliability in intelligent connected vehicles, crucial for advancing smart cities and intelligent transportation systems.
Researchers delve into the intricate relationship between speech pathology and the performance of deep learning-based automatic speaker verification (ASV) systems. The research investigates the influence of various speech disorders on ASV accuracy, providing insights into potential vulnerabilities in the systems. The findings contribute to a better understanding of speaker identification under diverse conditions, offering implications for applications in healthcare, security, and biometric authentication.
Researchers introduce artificial neural networks (ANNs) as a powerful tool for forecasting the generation of ten common types of demolition waste from buildings. Analyzing data from 150 buildings in South Korean redevelopment zones, the research develops specialized ANN prediction models for each waste category, achieving significant performance gains over past studies.
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.
Researchers introduce an innovative approach for speech-emotion analysis employing a multi-stage process involving spectro-temporal modulation, entropy features, convolutional neural networks, and a combined GC-ECOC classification model. Evaluating against Berlin and ShEMO datasets, the method showcases remarkable performance, achieving average accuracies of 93.33% and 85.73%, respectively, surpassing existing methods by at least 2.1% in accuracy and showing significant potential for improved emotion recognition in speech across various applications.
Researchers introduced and evaluated four metaheuristic algorithms—teaching–learning-based optimization, sine cosine algorithm, water cycle algorithm, and electromagnetic field optimization—integrated with a multi-layer perceptron neural network for predicting dissolved oxygen concentration in the Klamath River. These algorithms optimized computational variables, improving DO prediction accuracy in water quality assessment.
A recent article in Nature Machine Intelligence delves into the progress and challenges of Differentiable Visual Computing (DVC). The study proposes a unified DVC pipeline, integrating differentiable geometry, physics, and animation, enhancing data efficiency, accuracy, and speed in machine learning applications for real-world physical systems. The authors review key aspects, including rendering, animation, and geometry, highlighting the potential of DVC to bridge the gap between visual computing and deep learning.
This research proposes a novel approach to continual learning in artificial neural networks, addressing the challenge of balancing memory stability and learning plasticity. Inspired by the biological active forgetting mechanism observed in the Drosophila mushroom body’s γMB subset, the study introduces a synaptic expansion-renormalization framework, employing multiple learning modules to actively regulate forgetting.
This article in Nature features a groundbreaking approach for monitoring marine life behavior using Lite3D, a lightweight deep learning model. The real-time anomalous behavior recognition system, focusing on cobia and tilapia, outperforms traditional and AI-based methods, offering precision, speed, and efficiency. Lite3D's application in marine conservation holds promise for monitoring and protecting underwater ecosystems impacted by global warming and pollution.
This article features a groundbreaking 3D printing platform that integrates advanced machine vision, allowing real-time adjustments for precise material deposition. The vision-controlled system enables high-resolution, multi-material printing, eliminating the need for mechanical planarization and expanding the possibilities in creating intricate structures, from robotic hands to fluidic pumps, with potential applications across various domains like soft robotics and metamaterials.
This paper presents a novel approach for automatically counting manatees within a region using deep learning, even when provided with low-quality images. Manatees, being slow-moving aquatic mammals often found in aggregations in shallow waters, pose challenges such as water surface reflections, occlusion, and camouflage.
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.