这是我们最新精选的有关神经网络的全球英文出版物和专利，涉及许多科学在线期刊，分类并侧重于神经网络、人工神经元、纪元、神经架构、机器学习、深度学习和支持向量机。
An Edge-Deployable Multi-Modal Nano-Sensor Array Coupled with Deep Learning for Real-Time, Multi-Pollutant Water Quality Monitoring
Published on 2025-07-10 by Zhexu Xi, Robert Nicolas, Jiayi Wei @MDPI
Abstract: Real-time, high-resolution monitoring of chemically diverse water pollutants remains a critical challenge for smart water management. Here, we report a fully integrated, multi-modal nano-sensor array, combining graphene field-effect transistors, Ag/Au-nanostar surface-enhanced Raman spectroscopy substrates, and CdSe/ZnS quantum dot fluorescence, coupled to an edge-deployable CNN-LSTM architecture that fuses raw electrochemical, vibrational, and photoluminescent signals without manual feature eng[...]
Our summary: Edge-deployable nano-sensor array with deep learning for real-time water quality monitoring achieves high-resolution detection of diverse pollutants, enabling smart water management and rapid environmental incident response.
nano-sensor array, deep learning, water quality monitoring, multi-modal
Publication
Method and system for monitoring rock failure process
Patent published on the 2025-06-25 in ZA under Ref ZA202409026 by HUZHOU VOCATIONAL AND TECHNICAL COLLEGE [CN] (Niu Jiangrui [cn], Su Yingqiang [cn], Sun Lu [cn], Xie Enpu [cn])
Abstract: The invention discloses a method and a system for monitoring the rock failure process, which includes the following steps: acquiring comprehensive characteristic information of a rock sample; the acoustic emission signals of rock samples during the loading process are obtained in real time, and the spatial distribution characteristics of micro-cracks are determined by combining the comprehensive characteristic information; acquiring and preprocessing three-dimensional structural image data to ob[...]
Our summary: Method and system for monitoring rock failure process. Acquiring comprehensive characteristic information of a rock sample, determining spatial distribution characteristics of micro-cracks, and establishing a rock failure prediction model using machine learning algorithm.
rock failure process, monitoring system, acoustic emission signals, machine learning algorithm
Patent
Systems and methods for generating and using training data
Patent published on the 2025-05-22 in AU under Ref AU2024227696 by CANVA PTY LTD (Li Haitao)
Abstract: Systems and methods for automatically forming and using a training dataset for training a machine learning model are described. The method includes a) receiving an intent object and two or more design snapshots associated with the intent object, wherein the intent object indicates an intended design outcome and the two or more design snapshots include at least a first design snapshot indicating an initial state of a design and a second design snapshot indicating a state of the design after the i[...]
Our summary: Systems and methods for automatically generating and using training data for machine learning models by receiving intent objects and design snapshots, identifying design edits, and generating training datapoints.
training data, machine learning model, training dataset, design snapshots
Patent
Reconfiguring node topology in machine learning models
Patent published on the 2025-03-06 in WO under Ref WO2025048810 by STEM AI INC [US] (Goldstein Adam Julian Cisneros [us])
Abstract: Described is a system for dynamically reconfiguring a node topology by accessing a machine learning model configured to, in response to receiving input data received from an external source to the machine learning model, and applying the input data to the machine learning model. The application of the input data causes the machine learning model to perform: determining a first metric of the first group of nodes based on the input data, determining a second metric of the second group of nodes bas[...]
Our summary: System for dynamically reconfiguring node topology in machine learning models by comparing metrics of node groups and selecting, reconfiguring, and applying input data to generate inference output.
machine learning, node topology, reconfiguring, dynamic
Patent
Method, computer device, and computer program for network quantization using element-wise division-based rounding
Patent published on the 2025-03-06 in WO under Ref WO2025048024 by NAVER CLOUD CORP [KR] (Lee Jung Hyun [kr], Kim Jeonghoon [kr], Kwon Se Jung [kr], Lee Dongsoo [kr])
Abstract: Disclosed are a method, a computer device, and a computer program for network quantization using element-wise division-based rounding. The method for network quantization may comprise a step of performing, by at least one processor, quantization by applying a learnable parameter to a pre-learned weight of a neural network, wherein the step of performing quantization may quantize the pre-learned weight by means of an element-wise division-based rounding function using the parameter.[...]
Our summary: Method, computer device, and computer program for network quantization using element-wise division-based rounding.
network quantization, element-wise division, rounding, computer program
Patent
Method, apparatus, and medium for visual data processing
Patent published on the 2025-03-06 in WO under Ref WO2025049857 by BYTEDANCE INC [US] (Esenlik Semih [us], Zhang Zhaobin [us], Zhang Kai [us], Zhang Li [us])
Abstract: Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: obtaining, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, at least one intermediate representation of the visual data in the NN-based model; applying a first filter in the NN-based model on the at least one intermediate representation, at least one parameter of the first filter [...]
Our summary: Method for visual data processing with neural network-based model, including obtaining intermediate representation, applying first filter, and performing conversion.
neural network, visual data, processing, method
Patent
Computational exploration of the global microbiome for antibiotic discovery
Patent published on the 2025-03-06 in WO under Ref WO2025050118 by FUDAN UNIV [CN] (De La Fuente-nunez CÉsar [us], Der Torossian Torres Marcelo [us], Pedro Fragao Bento Coelho Luis [lu], Dias Santos JÚnior CÉlio [br])
Abstract: Novel antibiotics are needed to combat the antibiotic-resistance crisis. Presented herein are machine learning-based approaches for predicting antimicrobial peptides (AMPs) within the global microbiome and leverage a vast dataset that can include metagenomes and prokaryotic genomes from environmental and host-associated habitats to create a comprehensive catalog comprising distinct, non-redundant peptides, the majority of which are novel. This platform provides insights into the evolutionary ori[...]
Our summary: Computational exploration of global microbiome for antibiotic discovery using machine learning to predict antimicrobial peptides from metagenomes and prokaryotic genomes, validating predictions with synthesized peptides tested against drug-resistant pathogens and human gut commensals.
machine learning, antimicrobial peptides, metagenomes, antibiotic discovery
Patent
A Data-Driven, Predictive Approach to Real-Time Optimization of Quality
Published on 2025-02-28 by Asif Ullah, Muhammad Younas, Mohd Shahneel Saharudin @MDPI
Abstract: In the ever-changing world of modern manufacturing, maintaining product quality is of great importance, yet extremely difficult due to complexities and the dynamic production paradigm. Currently, quality is rather reactively measured through periodic inspections and manual assessments. Traditional quality management systems (QMS), through these reactive measures, are often inefficient because of their higher operational cost and delayed defect detection and mitigation. The paper introduces a nov[...]
Our summary: A cognitive twin framework enhances quality management in flexible manufacturing systems through real-time data analysis and proactive decision-making, resulting in significant improvements in total quality scores, defects per unit, scrap rate, and overall equipment efficiency.
Data-Driven, Predictive, Real-Time Optimization, Quality
Publication
