查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - A new study onNetworks is now available. According to news reporting originating from Selangor, Malaysia, by NewsRxcorrespondents, research stated, “This study introduces a novel, non-planar 16-port massive Multiple-Input-Multiple-Output (MIMO) antenna system that has been designed for six-generation (6G) THz futureapplications. On a cross-shaped of a 100 um thick Polyimide substrate, the proposed MIMO elements arepositioned strategically to encompass a wide frequency band of 61.54%.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - A new studyon sensor research is now available. According to news originating from Lima, Peru, by NewsRx editors,the research stated, “Gas turbines are thermoelectric plants with various applications, such as large-scaleelectricity production, petrochemical industry, and steam generation.”Funders for this research include Universidad Nacional De Ingenieria, Lima-peru.The news editors obtained a quote from the research from Universidad Nacional de Ingenieria: “In orderto optimize the operation of a gas turbine, it is necessary to develop system identification models thatallow for the development of studies and analyses to increase the system’s reliability. Current strategiesfor modeling complex and non-linear systems can be based on artificial intelligence techniques, usingautoregressive neural networks of the NARX and LSTM type. In this context, this work aims to develop amodel of a gas turbine capable of estimating the rotation speed of the turbine and simultaneously estimatingthe uncertainty associated with the estimation.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - Investigatorsdiscuss new findings in Engineering. According to news reporting out of Datong, People’s Republic of China,by NewsRx editors, research stated, “This paper focuses on the trajectory tracking problem of unmannedaerial vehicles (UAVs) under external disturbances, and a trajectory tracking method that combines modelpredictive control with dynamic neural networks was proposed. Firstly, the trajectory tracking problem istransformed into a constrained quadratic programming problem using the idea of model predictive control.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - Investigatorsdiscuss new findings in Information Technology. According to news reporting originating in Athens, Greece,by NewsRx journalists, research stated, “The demand for mobile data has been steadily increasing overthe last decade, forming an ever-increasing portion of the overall Internet traffic. A great portion of thisdemand is still served through capped cellular data plans that charge a fixed fee for data consumption upto a cap and impose a typically higher penalty rate for consumption beyond that cap.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - Current studyresults on Machine Learning have been published. According to news reporting from Taiyuan, People’s Republicof China, by NewsRx journalists, research stated, “Due to the large unexplored compositional space,long development cycle, and high cost of traditional trial-anderror experiments, designing high strengthaluminum-lithium alloys is a great challenge. This work establishes a performance-oriented machine learningdesign strategy for aluminum-lithium alloys to simplify and shorten the development cycle.”Funders for this research include National Natural Science Foundation of China (NSFC), NationalDefense Basic Scientific Research Program of China, Key Research and Development Program of ShanxiProvince.
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - Researchers detailnew data in networks. According to news reporting out of Hubei, People’s Republic of China, by NewsRxeditors, research stated, “Physics-informed neural networks (PINNs) have been used by researchers to solvepartial differential equation (PDE)-constrained problems. We evaluate PINNs to solve for frequency-domainacoustic wavefields.”The news correspondents obtained a quote from the research from China University of Geosciences:“PINNs can solely use PDEs to define the loss function for optimization without the need for labels. Partialderivatives of PDEs are calculated by mesh-free automatic differentiations. Thus, PINNs are free ofnumerical dispersion artifacts. It has been applied to the scattered acoustic wave equation, which reliedon boundary conditions (BCs) provided by the background analytical wavefield. For a more direct implementation,we solve the nonscattered acoustic wave equation, avoiding limitations related to relying onthe background homogeneous medium for BCs. Experiments support our following insights. Althoughsolving time-domain wave equations using PINNs does not require absorbing boundary conditions (ABCs),ABCs are required to ensure a unique solution for PINNs that solve frequency-domain wave equations,because the single-frequency wavefield is not localized and contains wavefield information over the fulldomain. However, it is not trivial to include the ABC in the PINN implementation, so we develop an adaptiveamplitude-scaled and phase-shifted sine activation function, which performs better than the previousimplementations. Because there are only two outputs for the fully connected neural network (FCNN),we validate a linearly shrinking FCNN that can achieve a comparable and even better accuracy with acheaper computational cost. However, there is a spectral bias problem, that is, PINNs learn low-frequencywavefields far more easily than higher frequencies, and the accuracy of higher frequency wavefields is oftenpoor.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - Research findingson Networks are discussed in a new report. According to news reporting originating in Baltimore, Maryland,by NewsRx journalists, research stated, “Fine-tuning deep neural networks (DNNs) for deployment hastraditionally relied on computationally intensive methods such as grid searches and neural architecturesearches, which may not consider hardware-aware metrics. Moreover, it is essential to consider multipleobjectives to develop a range of solutions for tiny machine learning hardware deployment with real-timelatency and low power constraints.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - Research findingson artificial intelligence are discussed in a new report. According to news reporting originating from Tokyo,Japan, by NewsRx correspondents, research stated, “Artificial Intelligence Technologies (AITs) have foundapplication in several domains, including the area of medicine.”Our news editors obtained a quote from the research from Tokyo Medical University: “Within thiscontext, AITs have been leveraged for purposes such as illness diagnosis and treatment, patient monitoring,and risk evaluation. By using Artificial Intelligence Technologies (AITs), it becomes feasible to createsystems that facilitate the development of intelligent models for predicting not only patients’ response totherapy but also the risk of illness. Due to the intricate and uncertain nature of these domains, a multitudeof scholars have developed AITs, including genetic algorithms, artificial immune systems, Artificial NeuralNetworks (ANN), and fuzzy logic. The integration of Fuzzy Logic Systems and ANN allows the constructionof intelligent and flexible systems. ANN gain novel information by changing the connections among itsdistinct layers. Fuzzy logic inference frameworks provide a computational model that is grounded on fuzzyset rules, theory, and fuzzy reasoning.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - New research onNetworks is the subject of a report. According to news reporting originating in Guildford, United Kingdom,by NewsRx journalists, research stated, “In this paper, we investigate the performance of a reconfigurableintelligent surface (RIS) assisted large-scale network by characterizing the coverage probability and theaverage achievable rate using stochastic geometry. Considering the spatial correlation between transmitters(TXs) and RISs, their locations are jointly modelled by a Gauss-Poisson process (GPP).”
查看更多>>摘要：By a News Reporter-Staff News Editor at Network Daily News - Investigatorsdiscuss new findings in physics. According to news reporting originating from the University of Notre Dameby NewsRx correspondents, research stated, “Traditional data-driven deep learning models often strugglewith high training costs, error accumulation, and poor generalizability in complex physical processes.”Financial supporters for this research include United States Department of Defense | United StatesNavy | Office of Naval Research; National Science Foundation.Our news correspondents obtained a quote from the research from University of Notre Dame: “Physicsinformeddeep learning (PiDL) addresses these challenges by incorporating physical principles into themodel. Most PiDL approaches regularize training by embedding governing equations into the loss function,yet this depends heavily on extensive hyperparameter tuning to weigh each loss term. To this end,we propose to leverage physics prior knowledge by ‘baking’ the discretized governing equations into theneural network architecture via the connection between the partial differential equations (PDE) operatorsand network structures, resulting in a PDE-preserved neural network (PPNN). This method, embeddingdiscretized PDEs through convolutional residual networks in a multi-resolution setting, largely improvesthe generalizability and long-term prediction accuracy, outperforming conventional black-box models.”
NETL
NSTL