摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-人工智能的新数据在一份新的报告中呈现。根据NewsRx记者在Kokushikan大学的新闻报道，研究表明，“这项研究需要检查和比较在冲压过程中通过液体废料检测获得的加速计信号和使用‘重心’方法获得的加速计信号中观察到的特征，后者通常用于通过机器学习进行异常检测。样本使用Mahalanobis-Taguchi系统检测。”新闻记者引用了国石馆大学的一篇研究文章：“如果使用重心法，包含无碎屑正常样本的单位空间不能从误差样本中分离出来，基于检测所有误差样本的设定阈值，上述方法的假阳性率为0.9%。”使用六个特征来估计允许系统检测100%错误样本S(且没有正常样本)的合适TH重新保持。使用S IX建议特征的检测比仅使用与新闻幻灯片向下行程相关的三个特征更有效。从两个不同事件中选择的特征(即，与仅从一个事件（即向下行程）中选择的特征相比，压载滑块的向下和向上行程可能导致更有效的检测。为了确认刀具磨损的影响，在创建所有误差样本后，根据正常样本进行六次实验。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on artificial intelligence are presented in a new report. According to news reporting from Kokushikan Unive rsity by NewsRx journalists, research stated, “This study entails an examination and comparison of features observed in an accelerometer signal obtained from fl oating-scrap detection during stamping with those obtained using the ‘center-of- gravity’ method, which is conventionally used for anomaly detection via machine learning. The samples are detected using the Mahalanobis-Taguchi system.” The news journalists obtained a quote from the research from Kokushikan Universi ty: “If using the center-of-gravity method, the unit space that contains normal samples without scraps cannot be separated from the error samples. Based on an e stimated threshold for detecting all the error samples, the falsepositive rate of the abovementioned method is 0.9 %. In this study, a suitable th reshold that allows the system to detect 100 % of the error sample s (and no normal samples) is estimated using six features. Detection using the s ix suggested features is more effective than that using only three features asso ciated with the downward journey of the press slide. Features selected from two different events (i.e., the downward and upward journeys of the press slide) may result in more effective detections than features selected from only one event (i.e., the downward journey). To confirm the effect of tool wear, six experiment s based on normal samples are conducted after all error samples are created.”
NETL
NSTL