Category
642 papers
Работа посвящена контролю качества данных в многоканальной телеметрии робототехнического манипулятора. Цель исследования – разработать и экспериментально оценить метод, который выявляет и локализует искаженный канал без обучения нейронной сети и без физического стенда. Метод объединяет показатели полноты, временной корректности и стабильности каждого потока с кинематическими и динамическими невязками между энкодерами, токами приводов, инерциальным каналом и внешней оценкой положения рабочего органа. Пороговые значения вычисляются по чистому калибровочному интервалу с использованием медианы и медианного абсолютного отклонения; локализация выполняется по графу межканальных связей. Воспроизводимый программный эксперимент включает 864 сценария, шесть видов искажений, четыре канала, три уровня интенсивности и двенадцать повторов. Предлагаемый метод достиг среднего F1 0,862 при 95-процентном бутстреп-интервале [0,845; 0,879], тогда как фиксированные правила и адаптивный одноканальный контроль дали 0,622 и 0,791 соответственно. Средняя точность локализации составила 0,843, доля ложных срабатываний – 0,0059. Наибольший выигрыш получен для постоянных смещений; для выбросов и замирания одноканальные методы оказались конкурентоспособнее. Результат представляет собой интерпретируемый модуль контроля входной телеметрии, пригодный для встраивания перед хранением и аналитической обработкой данных. The paper addresses data quality control in the multichannel telemetry of a robotic manipulator. The aim of the study is to develop and experimentally evaluate a method that detects and localises a corrupted channel without training a neural network and without a physical test bench. The method combines indicators of completeness, temporal correctness and stability of each stream with kinematic and dynamic residuals between the encoders, the drive currents, the inertial channel and the external estimate of the end-effector position. Threshold values are computed over a clean calibration interval using the median and the median absolute deviation; localisation is performed on a graph of inter-channel relations. The reproducible software experiment covers 864 scenarios, six types of distortion, four channels, three intensity levels and twelve repetitions. The proposed method reached a mean F1 of 0,862 with a 95% bootstrap interval [0,845; 0,879], whereas fixed rules and adaptive single-channel control yielded 0,622 and 0,791 respectively. The mean localisation accuracy was 0,843 and the false positive rate was 0,0059. The largest gain was obtained for constant offsets; for outliers and freezing, single-channel methods proved more competitive. The result is an interpretable module for input telemetry control suitable for embedding before data storage and analytical processing.
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is concluded that combining eye tracking and Thinking Aloud is feasible without compromising data quality and meaningful for comprehensive HCI evaluation.
A diagnostic support system based on a unified web platform that classifies patients according to the risks of developing three diseases based on regularly collected clinical or audio data using classical supervised learning algorithms is presented.
HawkEye is introduced, a modular, web-based vulnerability auditing platform designed to streamline security analysis by integrating multiple scanning tools within a unified dashboard and illustrates how consolidated reporting improves vulnerability prioritization for development teams.
Mortality among PLHIV in this study was associated with advanced disease, opportunistic diseases, commorbidities and abnormal laboratory findings, and Strengthening early diagnosis, management of opportunistic infections, and monitoring of clinical and laboratory indicators may help reduce mortality in this population.
The study observed reductions in glycaemic parameters after a nutrition promotion intervention in regulating the blood glucose levels among T2DM patients and supported the importance and effect of customised nutrition counselling and health education in diabetes management to improve glycaemic control.
The study presents the results of model experimental investigations and nonlinear numerical analyses of thin-walled, two-segment box structures with various configurations of integral corrugated stiffeners. The models for experimental testing were fabricated using additive manufacturing techniques. Five variants of the structure were examined, including a reference configuration without reinforcement. The experimental investigation was carried out using a dedicated test rig. Numerical representations of the investigated models were developed and subjected to nonlinear analyses using finite element method-based software. The adequacy of the numerical results was assessed through comparison with experimental data. The objective of the study was to determine the effect of different forms of the proposed structural solution on the magnitude of the critical load and the nature of post-buckling deformation.
The AE non CB and AE-CB phenotypes were found to have the most significant impact on HR-QoL among COPD patients, suggesting that individuals with the AE-CB phenotype notably require a tailored treatment approach that specifically addresses both the frequent exacerbations and the chronic bronchitis component to improve their overall QoL.
In a low throughout laboratory, fresh semen is a useful sample for daily quality control and Bland-Altman plot is an easy and effective tool for monitoring internal quality control when there are two assessors, obviating the need for complex statistical tests.
In his latest book, Professor Eugene Fitzgerald examines the forces that turn breakthroughs into value — and why innovation resists simple formulas.
MIT students designed, built, and tested a jet engine with AI copilots, assessing AI’s usefulness in developing high-performance aerospace systems.
Researchers developed an auditing technique to test generative AI models for malicious capabilities, without prompting them for illegal outputs.
A USAF cadet and a Lincoln Laboratory researcher found AI chatbots can help nontechnical service members produce viable software applications for their unique problems.
Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.
Education Innovation
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
