首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Studies Conducted at China University of Petroleum on Machine Learning Recently Published (Machine learning application in batch scheduling for multi-product pi pelines: A review)

    114-115页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news originating from Beijing, People’s Re public of China, by NewsRx correspondents, research stated, “Batch scheduling is a crucial part of pipeline enterprise operation management, especially in the c ontext of market-oriented operation.” Our news journalists obtained a quote from the research from China University of Petroleum: “It involves 3 main tasks: quickly preparing batch plans, accurately tracking interface movement, and operation condition in real time. Normally, th e completion of multi-product pipeline batch scheduling depends on simulation mo dels or optimization models and corresponding conventional solving algorithm. Ho wever, this approach becomes inefficient when applied to large-scale systems. Th e rapid development of machine learning has brought new ideas to batch schedulin g research. This paper first reviews the current state of batch scheduling techn ology, and suggests that applying machine learning to it is a promising developm ent direction. Then, we summarize the progress of machine learning applications in batch planning, interface movement tracking, and operational condition monito ring, and point out their limitations.”

    Studies from Georgia Institute of Technology in the Area of Robotics Described ( Kinematics and Stiffness Modeling of Soft Robot With a Concentric Backbone)

    115-116页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Robotics is the subjec t of a report. According to news reporting originating in Atlanta, Georgia, by N ewsRx journalists, research stated, “Soft robots can undergo large elastic defor mations and adapt to complex shapes. However, they lack the structural strength to withstand external loads due to the intrinsic compliance of fabrication mater ials (silicone or rubber).” Financial supporters for this research include This work was supported by Georgi a Tech IRIM and GTRI seed grant, Georgia Tech EVPR seed grant, and National Scie nce Foundation grant IIS-1718755., Georgia Tech IRIM, GTRI seed grant, Georgia T ech EVPR seed grant, National Science Foundation (NSF).

    Nile University of Nigeria Researchers Publish New Data on Machine Learning (Com parative studies of machine learning models for predicting higher heating values of biomass)

    116-116页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news reporting originating from Abuja, Nig eria, by NewsRx correspondents, research stated, “This study addresses the chall enge of efficiently determining the higher heating value (HHV) of biomass, a cru cial parameter in large-scale biomass-based energy systems.” Our news correspondents obtained a quote from the research from Nile University of Nigeria: “The conventional method of measuring HHV using an oxygen bomb calor imeter is time-consuming, expensive, and less accessible to researchers, particu larly in developing nations. To overcome these limitations, we employed four mac hine learning (ML) models, namely Random Forest (RF), Decision Tree (DT), Suppor t Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). These models we re developed by using proximate and ultimate analysis parameters as input featur es. Up to 200 datasets were compiled from literature and used for the ML models. Our results demonstrate the effectiveness of all ML models in accurately predic ting the HHV of biomass materials. Notably, the XGBoost model exhibited superior performance with the highest R-squared (R2) values for both training (0.9683) a nd test datasets (0.7309), along with the lowest root mean squared error (RSME) of 0.3558.”

    Researchers from Department of Chemical Engineering Report New Studies and Findi ngs in the Area of Artificial Intelligence (The Use of Artificial Intelligence I n Liquid Crystal Applications: a Review)

    117-117页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Artificial In telligence have been published. According to news reporting originating from Tor onto, Canada, by NewsRx correspondents, research stated, “Recent advancements in artificial intelligence (AI) have significantly influenced scientific discovery and analysis, including liquid crystals. This paper reviews the use of AI in pr edicting the properties of liquid crystals and improving their sensing applicati ons.” Financial support for this research came from Natural Sciences and Engineering R esearch Council of Canada (NSERC).

    Studies from Shandong University in the Area of Robotics Published (DSIL4IMR: A dual step-based initial localization method for industrial mobile robot)

    117-118页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on robotics have been published. According to news reporting out of Shandong University by NewsR x editors, research stated, “This paper introduces a dual-step based initial loc alization method for industrial mobile robots (DSIL4IMR) that operates without u ser intervention at start-up.” Our news editors obtained a quote from the research from Shandong University: “U tilizing a differential chassis equipped with a radar sensor, the method combine s feature extraction and spatial information matching steps to locate the robot’ s initial position. A unique metric, degree of stability, is developed to identi fy a feature map whether it is a dynamic or erroneous feature. DSIL4IMR does not require artificial landmarks and outperforms existing WiFi fingerprinting and m ap filter methods in both accuracy and efficiency.”

    Investigators from Sun Yat-sen University Zero in on Robotics (Modern Compliant Robot Control: Exploring Benefits From Singular Perturbation Synthesis)

    118-119页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Research findings on Robotics are disc ussed in a new report. According to news reporting originating in Shenzhen, Peop le’s Republic of China, by NewsRx journalists, research stated, “Singular pertur bation (SP)-based control is promising for flexible joint robots (FJRs) to achie ve high tracking accuracy under low implementation cost, and composite learning can achieve exact parameter estimation without persistent excitation. To exploit the benefits of SP-based control synthesis in the tracking control problem for FJRs with high degrees of freedom (DoFs), this article introduces five FJR contr ollers, including SP-based and non- SP-based controllers, for modern compliant r obots with high DoFs and nonnegligible joint elasticity.” Financial support for this research came from Fundamental Research Funds for the Central Universities, SunYat-sen University, China.

    Patent Issued for Intelligent precursory systematized authentication (USPTO 1206 9535)

    119-122页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – From Alexandria, Virginia, NewsRx jour nalists report that a patent by the inventors Gupta, Aarthi (Maharashtra, IN), M aharaja, Raja Arumugam (Tamil Nadu, IN), filed on February 9, 2022, was publishe d online on August 20, 2024. The patent’s assignee for patent number 12069535 is Bank of America Corporation (Charlotte, North Carolina, United States). News editors obtained the following quote from the background information suppli ed by the inventors: “Mobile and Internet resource event platforms allow for use rs (i.e., resource providers) to conduct resource events with other users (i.e., resource recipients). Typically, the resource provider is required to enter the resource recipient’s information (e.g., resource repository number, zip code, m obile telephone number or the like) into designated fields within the mobile app lication or webpage of the Internet resource event site in order to add a resour ce recipient to the resource provider’s list of verified resource recipients. Wh ile systems are in place to ensure that the entered information is associated wi th a valid resource recipient (i.e., the name and resource repository number mat chup or the like), currently limited means exist to ensure that the information that is being entered by the resource provider is, in fact, associated with the intended resource recipient. In one example, a resource provider may erroneously enter the resource recipient’s information and the incorrect information may ma tchup with an unintended but valid resource recipient. In another example, a pay or may be intentionally or unintentionally be provided the wrong resource recipi ent information (i.e., thinking they are transferring resources to the correct r esource recipient when, in fact, the information is associated with a another re source recipient (e.g., in the intentional case, a wrongdoer or the like).

    Researchers Submit Patent Application, 'Model-Based Attribution For Content Gene rated By An Artificial Intelligence (Ai)', for Approval (USPTO 20240281463)

    122-126页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – From Washington, D.C., NewsRx journali sts report that a patent application by the inventors AYKUT, Tamay (Pacifica, CA , US); KUHN, Christopher Benjamin (Munich, DE), filed on May 1, 2024, was made a vailable online on August 22, 2024. The patent’s assignee is Sureel Inc. (Pacifica, California, United States). News editors obtained the following quote from the background information suppli ed by the inventors: “ “Field of the Invention “This invention relates generally to systems and techniques to determine the pro portion of content items used by a generative artificial intelligence (e.g., Lat ent Diffusion Model or similar) to generate derivative content, thereby enabling attribution (and compensation) to content creators that created the content ite ms used to train the generative artificial intelligence to generate the derivati ve content.

    Patent Issued for Pallet transfer device for robot palletizing, a system for rob ot palletizing including the pallet transfer device and a method for robot palle tizing (USPTO 12065317)

    126-129页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – According to news reporting originatin g from Alexandria, Virginia, by NewsRx journalists, a patent by the inventor Lof qvist, Johan (Orebro, SE), filed on October 7, 2021, was published online on Aug ust 20, 2024. The assignee for this patent, patent number 12065317, is Robotautomation Svenska AB (Orebro, Sweden). Reporters obtained the following quote from the background information supplied by the inventors: “With the number of packets being sent today, efficient loadin g of packages on pallets is highly sought after. Systems for robot palletizing w here one robot loads and unloads packages to several pallets disposed around the robot are common. “Pallets are platforms used to move goods. There are different types of pallets, made of different materials and with different sizes. In recent times, standard ization of the size of pallets has occurred to a certain extent. For example, th ere is a widely used standard for European pallets known as the EUR Pallet.

    Researchers Submit Patent Application, 'Machine-Learning Model Generation', for Approval (USPTO 20240282452)

    129-133页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – From Washington, D.C., NewsRx journali sts report that a patent application by the inventors Markson, Christopher R. (H awthorne, NJ, US); Rajendran, Rahul (Dover, NJ, US); Shah, Pritesh J. (Paramus, NJ, US); Tyagi, Swati (Elkton, MD, US), filed on May 2, 2024, was made available online on August 22, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information suppli ed by the inventors: “Consumers provide feedback through a wide variety of chann els, such as social media, vendor websites, vendor call centers, mobile applicat ions, and online stores for mobile applications. The feedback typically is not c entrally available, and may be in a wide variety of formats, syntaxes, etc. Addi tionally, different consumers may use different words or phrases to provide feed back regarding the same topic.