As the translation of 機械状態特徴量を算出する特徴量算出部, which of the following is better?
1. A feature amount calculation unit that calculates a machine state feature amount.
2. A feature calculation unit that calculates a machine state feature.
ChatGPT:
Option 2 is the better choice:
"A feature calculation unit that calculates a machine state feature."
Here’s why:
- "Feature calculation unit" is more concise and natural in English compared to "feature amount calculation unit." The word "amount" is unnecessary, as "feature" by itself conveys the intended meaning.
- "Machine state feature" is clearer and more standard than "machine state feature amount." The term "feature" already implies a measurable aspect of the system, so "amount" is redundant.
In technical contexts, shorter, more direct phrases are often preferred for clarity. Therefore, Option 2 is both more conventional and concise.
US11468268(DASSAULT SYSTEMES [FR])
[0070] But many drawbacks are inherent to the existing methods. Some require manual supervision [18], and the others require a low variability of the shapes.
【0036】
しかし、既存の方法には多くの欠点がある。あるものは手動での監視を必要とし[18]、形について変動性が低いものもある。
Some methods also need very clean meshes to be able to compute accurate features.
また正確な特徴量を算出するのに非常にクリーンなメッシュも必要とする方法もある。
Some methods compute the alignment of all the dataset by a pairwise matching of each element with respect to one reference mesh, but are not able to leverage the whole dataset at once to compute a consistent frame.
また、いくつかの方法は、1つの基準メッシュに関して各要素のペアワイズマッチングを行うことにより、全てのデータセットの整列について算出するが、データセット全体を一度に活用して一貫したフレームを算出することができない。
Moreover, there is no fast way to co-align a new 3D model when the dataset has been aligned.
さらには、データセットを整列させたときに、新しい3Dモデルを同時整列させる高速な方法はない。
Finally, if some errors are made, manifold learning cannot correct the mistakes in the alignment without learning all the possible rotations with data augmentation.
最後に、何らかのエラーが発生した場合、畳み込み学習では、可能性のある全ての回転についてデータの拡大を伴いつつ、学習することなしには、整列における誤りを訂正することができない。
The same drawbacks apply also to co-segmentation methods.
同様の欠点が、同時セグメント化法にも当てはまる。
EP4334941(ELUCID BIOIMAGING INC [US])
The virtual ‘omics engine 310 is configured to receive the test subject data 302b and generate virtual ‘omics data 312.
仮想オーミクスエンジン310は、被験者データ302bを受け取り、仮想オーミクスデータ312を生成するように構成される。
The test subject data 302b include computed tomography angiograph (CTA) imaging data of a plaque from the test subject, plaque morphology data, and proteomics data corresponding to the test subject.
被験者データ302bは、被験者からのプラークのコンピュータ断層血管造影(CTA)イメージングデータ、プラーク形態データ、および被験者に対応するプロテオミクスデータを含む。
As shown in FIG. 6B, molecular measurements such as protein levels (proteomics) and gene expressions (transcriptomics) can be estimated based on a comparison between CTA images used in training the virtual ‘omics engine 310 and a patient’s CTA image not used in training.
図6Bに示されるように、タンパク質レベル(プロテオミクス)および遺伝子発現(トランスクリプトミクス)などの分子測定結果が、仮想オーミクスエンジン310を訓練する際に使用されるCTA画像と、訓練に使用されない患者のCTA画像との比較に基づいて推定され得る。
The test subject data 302b correspond to the data used to train the virtual ‘omics engine 310.
被験者データ302bは、仮想オーミクスエンジン310を訓練するために使用されるデータに対応する。
During training, the virtual ‘omics engine 310 identifies features in CTA imaging data (e.g., a particular plaque morphology) that are predictive of the molecular measurements.
訓練の間、仮想オーミクスエンジン310は、分子測定結果を予測するものであるCTAイメージングデータ(たとえば、特定のプラーク形態)の中の特徴量を特定する。