期刊,Robotics & Machine Learning Daily News 2024年卷Feb.5期_国家学术搜索

Patent Application Titled 'Text Classification via Term Mapping and Machine-learning Classification Model' Published Online(USPTO 20240020474)

133-137页

查看更多>>摘要：According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors Akers, Peter Todd (North Potomac, MD, US); Barnes, Catherine (Glen Allen, VA, US); Honermann, Jennifer (Glen Allen, VA, US), filed on July 14, 2022, was made available online on January 18, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “Determining subject matter contained in text is tedious. While machine-based manipulations of the text may provide simplistic analyses including word frequencies and other calculatable values, collections of mere numbers fail to adequately enable one to identify the subject matter of text. Further, where the text appears across multiple documents with limited quantities of text in each document, machine-based manipulations are inadequate to summarize the content of each document or summarize the collection of documents.” In addition to obtaining background information on this patent application, NewsRx editors also ob- tained the inventors' summary information for this patent application: “The following presents a simplified summary of various aspects described herein. This summary is not an extensive overview, and is not intended to identify key or critical elements or to delineate the scope of the claims. The following sum- mary merely presents some concepts in a simplified form as an introductory prelude to the more detailed description provided below.

原文链接:

NETL
NSTL

Researchers Submit Patent Application, 'Smart Automatic Skip Mode', for Approval (USPTO 20240022774)

137-140页

查看更多>>摘要：From Washington, D.C., NewsRx journalists report that a patent application by the inventors Campbell, Jeffrey (Long Beach, CA, US); Glaser, Twain (Long Beach, CA, US); Konrath, Kristopher (Long Beach, CA, US); Webb, Steven (Long Beach, CA, US), filed on July 14, 2023, was made available online on January 18, 2024. The patent's assignee is Relativity Space Inc. (Long Beach, California, United States). News editors obtained the following quote from the background information supplied by the inventors: “Additive manufacturing is a process by which a product or part is manufactured by adding material progressively to the base printed structure in a sequence or pattern that would result in a solid part being built. This method of manufacturing is commonly referred to as three dimensional or 3-D printing and can be done with various materials, including but not limited to plastics and metals. “3-D printing machines utilize a build plate to act as a base for printing the desired part. The feed material is placed or printed onto the build plate in sequential beads or dots which builds into sequential layers. 3D printers, including metal and polymer printers, require a smooth and flat surface to start each new print. Metal 3D printers use a metallic build plate that is typically CNC machined to achieve the appropriate surface finish (smoothness) and flatness.”

原文链接:

NETL
NSTL

Researchers Submit Patent Application, 'Modular Metal 3-D Printer Build Plate', for Approval (USPTO 20240017490)

140-144页

查看更多>>摘要：From Washington, D.C., NewsRx journalists report that a patent application by the inventors Campbell, Jeffrey (Long Beach, CA, US); Glaser, Twain (Long Beach, CA, US); Konrath, Kristopher (Long Beach, CA, US); Webb, Steven (Long Beach, CA, US), filed on July 14, 2023, was made available online on January 18, 2024. The patent's assignee is Relativity Space Inc. (Long Beach, California, United States). News editors obtained the following quote from the background information supplied by the inventors: “Additive manufacturing is a process by which a product or part is manufactured by adding material progressively to the base printed structure in a sequence or pattern that would result in a solid part being built. This method of manufacturing is commonly referred to as three dimensional or 3-D printing and can be done with various materials, including but not limited to plastics and metals. “3-D printing machines utilize a build plate to act as a base for printing the desired part. The feed material is placed or printed onto the build plate in sequential beads or dots which builds into sequential layers. 3D printers, including metal and polymer printers, require a smooth and flat surface to start each new print. Metal 3D printers use a metallic build plate that is typically CNC machined to achieve the appropriate surface finish (smoothness) and flatness.”

原文链接:

NETL
NSTL

Patent Application Titled 'Robotic Cleaner' Published Online (USPTO 20240016354)

144-147页

查看更多>>摘要：According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors BRUNNER, Charles S. (Stockton, NJ, US); MATHIEU, Margaret (East Greenwich, RI, US), filed on June 20, 2023, was made available online on January 18, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “The following is not an admission that anything discussed below is part of the prior art or part of the common general knowledge of a person skilled in the art. “A surface cleaning apparatus may be used to clean a variety of surfaces. Some surface cleaning apparatuses include a rotating agitator (e.g., brush roll). One example of a surface cleaning apparatus includes a vacuum cleaner which may include a rotating agitator as well as a vacuum source. Non-limiting examples of cleaners include robotic vacuums, robotic sweepers, multi-surface robotic cleaners, wet/dry robotic cleaners, upright vacuum cleaners, canister vacuum cleaners, stick vacuum cleaners, and central vacuum systems. “Within the field of robotic and autonomous cleaning devices, there are a range of form factors and features that have been developed to meet a range of cleaning requirements. However, certain cleaning applications remain a challenge.

原文链接:

NETL
NSTL

Patent Application Titled 'Logistics Robotic System' Published Online (USPTO 20240017399)

147-150页

查看更多>>摘要：According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventor REST, Adam Ming (Pittsburgh, PA, US), filed on July 12, 2022, was made available online on January 18, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “The present disclosure relates in general to a robotic system for handling cargo, and is more particularly directed to robotic loading and unloading systems for automatically loading or unloading logistic containers. Logistic containers loaded with cargo are moved around the world to deliver products to loading and unloading warehouses. Manually loading and unloading items from and/or to logistic containers is arduous, repetitive. and injury-prone making these jobs notoriously difficult to fill with high turnover rates. Automated robotic alternatives have been used to help loading and unloading logistic containers. However, these alternatives are plagued by technical challenges and limitations. Through applied effort, ingenuity, and innovation, many of these identified problems have been solved by developing solutions that are included in embodiments of the present disclosure, many examples of which are described in detail herein.”

原文链接:

NETL
NSTL

Patent Issued for Suspension system for remote catheter guidance (USPTO 11872003)

150-153页

查看更多>>摘要：From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Olson, Eric S. (Maplewood, MN, US), filed on October 13, 2021, was published online on January 16, 2024. The patent's assignee for patent number 11872003 is St. Jude Medical (St. Paul, Minnesota, United States). News editors obtained the following quote from the background information supplied by the inventors: “a. Field “This disclosure relates to robotic catheter systems, apparatuses, and methods for automated control of a catheter and related components. In particular, the instant disclosure relates to a suspension system for a robotic catheter system for manipulating a catheter and related components.

原文链接:

NETL
NSTL

CoSpred: Machine learning workflow to predict tandem mass spectrum in proteomics

153-154页

查看更多>>摘要：According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from biorxiv.org: “In mass spectrometry-based proteomics, the identification and quantification of peptides and proteins is usually done using database search algorithms or spectral library matching. The use of deep learning algorithms can help improve the identification rates of peptides and proteins through the generation of high-fidelity theoretical spectrum which can be used as the basis of a more complete spectral library than those presently available. Current methods focus on predicting only backbone ions, such as y- and b- ions. “However, the inclusion of non-backbone ions is necessary to truly improve spectral library matching. “Here we focus on providing a user-friendly machine learning workflow, which we call Complete Spectrum Predictor (CoSpred). Using CoSpred users can create their own machine learning compatible training dataset and then train a Machine Learning model to predict both backbone and non-backbone ions. For the model a transformer encoder architecture is used to predict the complete MS/MS spectrum from a given peptide sequence. This model does not require background knowledge of fragment ion annotations or fragmentation rules. The model outputs the set of pairs (Mi, Ii) where Mi is the m/z (mass-to-charge ratio) of a peak in the spectrum and Ii is the intensity of the peak. The model presented here for validation was trained on the dataset available in the MassIVE data repository and shows superior performance in terms of various metrics (e.g. precision/recall for mass, cosine similarity for peak intensity, etc) between the true and predicted spectra.

原文链接:

NETL
NSTL