期刊,Robotics & Machine Learning Daily News 2024年卷Jun.25期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

Study Results from Computer Science Department Update Understanding of Machine L earning (Supervised Machine Learning a Brief Survey of Approaches)

78-79页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Research findings on artificial intelligence are discussed in a new report. According to news reporting out of the Computer Scien ce Department by NewsRx editors, research stated, "Machine learning has become p opular across several disciplines right now. It enables machines to automaticall y learn from data and make predictions without the need for explicit programming or human intervention." The news journalists obtained a quote from the research from Computer Science De partment: "Supervised machine learning is a popular approach to creating artific ial intelligence. A computer algorithm is trained on input data that has been la beled for a certain output, making it one of two major areas of machine learning that has seen a lot of successful research. The model is trained until it can i dentify the underlying correlations and patterns between the input and output la bels, enabling it to generate accurate labeling results when confronted with une xplored data. Supervised learning is good at solving classification and regressi on problems. The problem of regression occurs when the outputs are continuous, w hile the problem of classification occurs when the outputs are categorical. We w ill concentrate on the benefits and drawbacks of supervised learning algorithms in this review. Creating a precise model of the distribution of class labels in terms of predictor features is the aim of supervised learning."

原文链接:

NETL
NSTL

Report Summarizes Robotics Study Findings from Inner Mongolia University of Scie nce and Technology (Group-weighted Oscillatory Containment for Multiple Robots U nder Heterogeneous Cooperation and Competition)

79-80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 originating from Baotou, People's Repub lic of China, by NewsRx correspondents, research stated, "The group-weighted con tainment (GWC) problem is studied for swarms of robots, where the information fl ow among agents is heterogeneous (weighted) cooperative-competitive and the whol e networked systems are composed of multiple different groups. Each group is for med by multiple harmonic oscillator leaders and multiple robot followers governe d by Euler-Lagrange (EL) equations." Funders for this research include National Natural Science Foundation of China ( NSFC), Program for Young Talents of Science and Technology in Universities of In ner Mongolia Autonomous Region, Fundamental Research Funds for Inner Mongolia Un iversity of Science Technology, Natural Science Foundation of Inner Mongolia Aut onomous Region of China, Key Laboratory of Synthetical Automation for Process In dustries at Universities of Inner Mongolia Autonomous Region.

原文链接:

NETL
NSTL

University of Alberta Researcher Broadens Understanding of Machine Learning (A C omparison of Bias Mitigation Techniques for Educational Classification Tasks Usi ng Supervised Machine Learning)

80-81页

查看更多>>摘要：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 originating from Edmonton, Cana da, by NewsRx editors, the research stated, "Machine learning (ML) has become in tegral in educational decision-making through technologies such as learning anal ytics and educational data mining. However, the adoption of machine learning-dri ven tools without scrutiny risks perpetuating biases." The news reporters obtained a quote from the research from University of Alberta : "Despite ongoing efforts to tackle fairness issues, their application to educa tional datasets remains limited. To address the mentioned gap in the literature, this research evaluates the effectiveness of four bias mitigation techniques in an educational dataset aiming at predicting students' dropout rate. The overarc hing research question is: "How effective are the techniques of reweighting, res ampling, and Reject Option-based Classification (ROC) pivoting in mitigating the predictive bias associated with high school dropout rates in the HSLS:09 datase t?' The effectiveness of these techniques was assessed based on performance metr ics including false positive rate (FPR), accuracy, and F1 score. The study focus ed on the biological sex of students as the protected attribute. The reweighting technique was found to be ineffective, showing results identical to the baselin e condition. Both uniform and preferential resampling techniques significantly r educed predictive bias, especially in the FPR metric but at the cost of reduced accuracy and F1 scores."

原文链接:

NETL
NSTL

Guangdong University of Technology Researcher Updates Current Study Findings on Robotics (Semi-Supervised Informer for the Compound Fault Diagnosis of Industria l Robots)

81-82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 new report. According to news reporting originating from Guangzhou, Peopl e's Republic of China, by NewsRx correspondents, research stated, "The increasin g deployment of industrial robots in manufacturing requires accurate fault diagn osis." The news journalists obtained a quote from the research from Guangdong Universit y of Technology: "Online monitoring data typically consist of a large volume of unlabeled data and a small quantity of labeled data. Conventional intelligent di agnosis methods heavily rely on supervised learning with abundant labeled data." According to the news reporters, the research concluded: "To address this issue, this paper presents a semi-supervised Informer algorithm for fault diagnosis mo deling, leveraging the Informer model's longand short-term memory capabilities and the benefits of semi-supervised learning to handle the diagnosis of a small amount of labeled data alongside a substantial amount of unlabeled data. An exp erimental study is conducted using real-world industrial robot monitoring data t o assess the proposed algorithm's effectiveness, demonstrating its ability to de liver accurate fault diagnosis despite limited labeled samples."

原文链接:

NETL
NSTL

Findings on Machine Learning Detailed by Investigators at University of Copenhag en (Markov-switching Decision Trees)

82-83页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Machine Learning are pre sented in a new report. According to news reporting from Copenhagen, Denmark, by NewsRx journalists, research stated, "Decision trees constitute a simple yet po werful and interpretable machine learning tool. While tree-based methods are des igned only for cross-sectional data, we propose an approach that combines decisi on trees with time series modeling and thereby bridges the gap between machine l earning and statistics." Financial support for this research came from Universitt Bielefeld (3146). The news correspondents obtained a quote from the research from the University o f Copenhagen, "In particular, we combine decision trees with hidden Markov model s where, for any time point, an underlying (hidden) Markov chain selects the tre e that generates the corresponding observation. We propose an estimation approac h that is based on the expectation-maximisation algorithm and assess its feasibi lity in simulation experiments. In our real-data application, we use eight seaso ns of National Football League (NFL) data to predict play calls conditional on c ovariates, such as the current quarter and the score, where the model's states c an be linked to the teams' strategies."

原文链接:

NETL
NSTL

Fujian Cancer Hospital Reports Findings in Gastrointestinal Stromal Tumors [Robot-assisted laparoscopic combined with endoscopic partial gastrectomy (RALE-P G) for the treatment of gastric gastrointestinal stromal tumors in challenging a natomical ...]

83-84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 Digestive System Disea ses and Conditions - Gastrointestinal Stromal Tumors is the subject of a report. According to news reporting out of Fuzhou, People's Republic of China, by NewsR x editors, research stated, "Gastric gastrointestinal stromal tumors in challeng ing anatomical locations are difficult to remove. This study retrospectively ana lyzed the clinical data of 12 patients with gastric GISTs in challenging anatomi cal locations who underwent robot-assisted laparoscopic combined with endoscopic partial gastrectomy (RALE-PG) and manual suturing of the gastric wall." Our news journalists obtained a quote from the research from Fujian Cancer Hospi tal, "This study included 12 patients with a mean age of 56.8 ? 9.8 years and a mean BMI of 23.9 ? 1.9 kg/m. Tumors were located in the GEJ ( = 3), lesser curva ture ( = 3), posterior gastric wall ( = 3) and antrum ( = 3). The cardia and pyl orus were successfully preserved in all patients regardless of the tumor locatio n. The mean tumor size was 4.5 ? 1.4 cm. The mitotic-count/50 mm was less than 5 in all patients (100%). There was no intraoperative tumor rupture (0%) and no conversion to open surgery (0%). The media n operation time was 122 (97-240) min, and the median blood loss volume was 10 ( 5-30) ml. The median postoperative VAS score was 2 (2-4). The median time to fir st flatus was 2 (2-3) days. The median time to first fluid intake was 2 (2-3) da ys. The median time to first ambulation after the operation was 3 (2-4) days. No cases of anastomotic stenosis or leakage were found. The median time to drain r emoval for 6 patients was 5 (4-7) days. The median time to nasogastric tube remo val for all patients was 2 (1-5) days. The median postoperative hospital stay wa s 5 (4-8) days. One patient (female/41 year) developed moderate anemia (Clavien- Dindo grade II complication). There was no unplanned readmission within 30 days after the operation. The median distance from the tumor to the resection margin was 1 (1-2) cm. R0 resection was achieved in all patients. The median follow-up period was 19 (10-25) months, and all patients survived with no recurrence or me tastasis. RALE-PG is a safe, feasible and advantageous technique for treating GI STs in challenging anatomical locations."

原文链接:

NETL
NSTL

Studies from De La Salle University Provide New Data on Machine Learning (Predic tion of Soil Liquefaction Triggering Using Rule- Based Interpretable Machine Lear ning)

84-85页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ar tificial intelligence. According to news reporting originating from Manila, Phil ippines, by NewsRx correspondents, research stated, "Seismic events remain a sig nificant threat, causing loss of life and extensive damage in vulnerable regions ." Financial supporters for this research include Department of Science And Technol ogy Engineering Research And Development For Technology. Our news reporters obtained a quote from the research from De La Salle Universit y: "Soil liquefaction, a complex phenomenon where soil particles lose confinemen t, poses a substantial risk. The existing conventional simplified procedures, an d some current machine learning techniques, for liquefaction assessment reveal l imitations and disadvantages. Utilizing the publicly available liquefaction case history database, this study aimed to produce a rule-based liquefaction trigger ing classification model using rough set-based machine learning, which is an int erpretable machine learning tool. Following a series of procedures, a set of 32 rules in the form of IF-THEN statements were chosen as the best rule set. While some rules showed the expected outputs, there are several rules that presented a ttribute threshold values for triggering liquefaction. Rules that govern fine-gr ained soils emerged and challenged some of the common understandings of soil liq uefaction."

原文链接:

NETL
NSTL

Study Results from Penza State Technological University in the Area of Artificia l Intelligence Published (Matching visually observed 3D model to original refere nce object)

85-85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 from Penza State Technologi cal University by NewsRx journalists, research stated, "In the development of a visual environment simulator or a thermal imager simulator, one of the challenge s encountered when assessing the external appearance of engineering structures i s the need to ensure the correspondence of the developed 3D model of a reference object to the original 3D object." The news journalists obtained a quote from the research from Penza State Technol ogical University: "Since creating a complete model is currently impractical, th e criterion for assessment is based on the conformity of forming specified compo nents of the cognitive model of a human observer necessary in their professional activities. Research has shown that to address this challenge, it is advisable to choose one of the artificial intelligence methods to entrust it with the task of evaluating the developed 3D model and minimize the subjectivity in the decis ion-making process of ‘whether the external appearance of the 3D model meets the client's requirements.' The article proposes using deductive reasoning in ChatG PT to assess the conformity of the external appearance of a 3D model to a specif ied 3D object by representing the model as incomplete sequences and evaluating i ts ability to complete them in accordance with conclusions made by humans. The s uggested approach involves solving the problem based on scenarios where humans f ormulate logical conclusions from provided information, followed by the applicat ion of ChatGPT in processing the presented sequences of conclusions. A comparati ve analysis is presented to determine the extent to which ChatGPT demonstrates d eductive reasoning and how closely it aligns with human deductive models."

原文链接:

NETL
NSTL

Patent Issued for Real-time content integration based on machine learned selecti ons (USPTO 12003577)

86-89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 Brewer, Jason (Marina del Rey, CA, US), Farnham, Rodrigo B. (Los Angeles, CA, US), Lue, David B. (Santa Monica, CA , US), Stucky-Mack, Nicholas J. (Los Angeles, CA, US), filed on January 19, 2023 , was published online on June 4, 2024. The patent's assignee for patent number 12003577 is Snap Inc. (Santa Monica, Cal ifornia, United States). News editors obtained the following quote from the background information suppli ed by the inventors: "Users can execute applications on their mobile client devi ces to receive posts and collections of content published by other users. For ex ample, a user may browse content within an application and select a content item (e.g., slideshow, article) for viewing. When the content is requested, the serv er handling the request must assemble the content, some of which may be provided by third parties, on-the-fly and send the assembled content to the user before the user notices a delay. The limited amount of time and limited network bandwid th constrain how content is selected for display." As a supplement to the background information on this patent, NewsRx corresponde nts also obtained the inventors' summary information for this patent: "The descr iption that follows includes systems, methods, techniques, instruction sequences , and computing machine program products that embody illustrative embodiments of the disclosure. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide an understanding of various embodiments of the inventive subject matter. It will be evident, however , to those skilled in the art, that embodiments of the inventive subject matter may be practiced without these specific details. In general, well-known instruct ion instances, protocols, structures, and techniques are not necessarily shown i n detail.

原文链接:

NETL
NSTL

Researchers Submit Patent Application, 'Method For Performing Membership Inferen ce Attack Against Generative Models And Apparatus For The Same', for Approval (U SPTO 20240185068)

89-93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 HUR, Jun Beom (Yongin-si, KR); LIM, Gyeong Sup (Seoul, KR); OH, Won Jun (Seoul, KR); YANG, Bo Sung (Suwon- si, KR), filed on November 30, 2023, was made available online on June 6, 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: " "The present invention relates to a method for performing a membership inference attack against generative models and an apparatus for the same. More specifical ly, the present invention relates to a method for performing a membership infere nce attack against generative models and an apparatus for the same, which can fu ndamentally prevent the occurrence of early convergence, which is the primary dr awback of generative models, to thereby improve the learning performance of an a ttack model.

原文链接:

NETL
NSTL