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

    Research on Machine Learning Published by a Researcher at Imperial College Londo n (Machine learning with requirements: A manifesto)

    49-50页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New study results on artificial intell igence have been published. According to news reporting out of London, United Ki ngdom, by NewsRx editors, research stated, “In the recent years machine learnin g has made great advancements that have been at the root of many breakthroughs i n different application domains.” The news reporters obtained a quote from the research from Imperial College Lond on: “However, it is still an open issue how to make them applicable to high-stak es or safety-critical application domains, as they can often be brittle and unre liable. In this paper, we argue that requirements definition and satisfaction ca n go a long way to make machine learning models even more fitting to the real wo rld, especially in critical domains. To this end, we present two problems in whi ch (i) requirements arise naturally, (ii) machine learning models are or can be fruitfully deployed, and (iii) neglecting the requirements can have dramatic con sequences. Our proposed pyramid development process integrates requirements spec ification into every stage of the machine learning pipeline, ensuring mutual inf luence between requirements and subsequent phases.”
      原文链接:
    • NETL
    • NSTL

    Researcher from University of Central Florida Describes Findings in Robotics (Us er-centered Social Interaction Design in Intelligent Personal Assistants and Soc ial Robots)

    49-49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 originating from Orlando, Florida, by NewsRx correspondents, research stated, “User-centered design practices are used to dev elop the social interaction characteristics of intelligent personal assistants a nd social robots.” The news editors obtained a quote from the research from University of Central F lorida: “In this approach, developers establish characteristics favored by the m ajority of users. However, catering to target users may negate the benefits in u ser experience and use intention achieved from matching a product’s characterist ics to the preferences of individual users. The present study examines differenc es between target versus individual user based approaches to user-centered desig n. Specifically, a framework is presented on how to develop a product to meet in dividual user preferences.” According to the news editors, the research concluded: “Results show that indivi dual user preferences, while similar to the target user preferences, can vary si gnificantly from the baseline. Machine learning and artificial intelligence appr oaches should be employed to help adjust social interaction approaches from a ba seline to individual user preferences.”
      原文链接:
    • NETL
    • NSTL

    Lausanne University Hospital Reports Findings in Robotics (Ondemand robotics-Th e best of both worlds for robotic-assisted laparoscopic surgery)

    50-51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 out of Lausanne, Switzerland, by News Rx editors, research stated, “A modular, combined use of robotic and laparoscopi c platforms has been suggested to address challenges in optimal workspace utiliz ation. The 3-arm on-demand open Dexter Robotic System was developed to combine t he advantages of robot-assisted precision surgery in narrow spaces with the lapa roscopic approach for frequent position changes in larger spaces.” Our news journalists obtained a quote from the research from Lausanne University Hospital, “The system integrates 2 patient carts, a fully controllable endoscop e arm, and a sterile surgeon open console, allowing for a rapid switch between r obot-assisted surgery and laparoscopy. When switching, the robotic arms may be f olded into a laparoscopic home position at any time during a procedure, allowing unrestricted access to the patient. Switches take 15-30 seconds, occurring seam lessly without redocking or recalibrating upon returning to the robotic mode. Du ring oncologic colorectal resections, some procedure steps (eg, central vessel l igation and lymphadenectomy) are best suited for the robotic approach, providing advantages related to 3-dimensional vision, improved ergonomics, and improved d exterity within confined spaces. In contrast, the laparoscopic platform is bette r suited for procedure steps requiring frequent movements within a large workspa ce (eg, lateral to medial mobilization of the colon). The Dexter system provides a portfolio of 7 robotic instruments with monopolar and bipolar function operat ing with any existing available generator. Furthermore, existing operating room equipment, including insufflating devices, optics, and trocars can be used with the Dexter robotic platform.”
      原文链接:
    • NETL
    • NSTL

    Study Data from George Mason University Update Understanding of Robotics (Compro mise in Human-Robot Collaboration for Threat Assessment)

    51-52页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on robotics have been pr esented. According to news originating from Fairfax, Virginia, by NewsRx editors , the research stated, “Advancements in Artificial Intelligence (AI) will produc e “reasonable disagreements” between human operators and machine partners.” Financial supporters for this research include Air Force Office of Scientific Re search. Our news journalists obtained a quote from the research from George Mason Univer sity: “A simulation study investigated factors that may influence compromise bet ween human and robot partners when they disagree in situation evaluation. Eighty -seven participants viewed urban scenes and interacted with a robot partner to m ake a threat assessment. We explored the impacts of multiple factors on threat r atings and trust, including how the robot communicated with the person, and whet her or not the robot compromised following dialogue. Results showed that partici pants were open to compromise with the robot, especially when the robot detected threat in a seemingly safe scene.”
      原文链接:
    • NETL
    • NSTL

    Study Results from Seoul National University Broaden Understanding of Machine Le arning (Machine learning on quantum experimental data toward solving quantum man y-body problems)

    52-52页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Investigators publish new report on artificial in telligence. According to news reporting from Seoul National University by NewsRx journalists, research stated, “Advancements in the implementation of quantum ha rdware have enabled the acquisition of data that are intractable for emulation w ith classical computers.” Funders for this research include National Research Foundation of Korea; Korea B asic Science Institute. The news journalists obtained a quote from the research from Seoul National Univ ersity: “The integration of classical machine learning (ML) algorithms with thes e data holds potential for unveiling obscure patterns. Although this hybrid appr oach extends the class of efficiently solvable problems compared to using only c lassical computers, this approach has been only realized for solving restricted problems because of the prevalence of noise in current quantum computers. Here, we extend the applicability of the hybrid approach to problems of interest in ma ny-body physics, such as predicting the properties of the ground state of a give n Hamiltonian and classifying quantum phases. By performing experiments with var ious error-reducing procedures on superconducting quantum hardware with 127 qubi ts, we managed to acquire refined data from the quantum computer. This enabled u s to demonstrate the successful implementation of theoretically suggested classi cal ML algorithms for systems with up to 44 qubits.”
      原文链接:
    • NETL
    • NSTL

    University Hospital Mannheim Reports Findings in Liver Malignancy [Robotic versus laparoscopic hepatectomy for liver malignancies (ROC’N’ROLL): a s ingle-centre, randomised, controlled, singleblinded clinical trial]

    53-53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 Oncology - Liver Malig nancy is the subject of a report. According to news reporting originating from M annheim, Germany, by NewsRx correspondents, research stated, “Robotic hepatectom y (RH) has been increasingly adopted for the treatment of liver malignancies des pite lacking evidence from randomised trials. We aimed to determine the effect o f RH compared to laparoscopic hepatectomy (LH) on quality of life in patients un dergoing minimally invasive hepatectomy for liver malignancies.” Our news editors obtained a quote from the research from University Hospital Man nheim, “This singleblinded, randomised trial was conducted at a tertiary care a cademic centre (DRKS00027531). Patients with resectable liver malignancies were assessed for eligibility and randomly assigned to either RH or LH with stratific ation by type of malignancy and difficulty of resection. Patients were blinded t o the treatment allocation. The primary outcome was the mean quality of life wit hin 90 days after surgery, measured with the role functioning scale of the Europ ean Organisation for Research and Treatment of Cancer QLQ-C30 questionnaire. Sec ondary outcomes included operating time, morbidity, blood loss, conversion rate, postoperative recovery, and resection margin status. Between February 21, 2022, and Sep 18, 2023, 80 patients (RH: n = 41, LH: n = 39) were included and analys ed on an intention-to-treat basis. Role functioning scores did not differ betwee n RH and LH (mean [SD], 74.3 [23.3] versus 79.6 [22.3] ; mean difference -5.3, 95% CI -15.6 to 5.1, p = 0.547). The compr ehensive complication index was not significantly different between the study gr oups (8.9 [23.1] versus 15.5 [23.9], p = 0.137). There were no differences in other periope rative outcomes.”
      原文链接:
    • NETL
    • NSTL

    Researchers from Chinese Academy of Sciences Describe Findings in Machine Learni ng (Predicting Heat Capacity of Molecular Fluids Using Interpretable Machine Lea rning Model)

    54-54页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Machine Learning. According to news reporting originating from Beijing, People’s Republ ic of China, by NewsRx correspondents, research stated, “Heat capacity at consta nt pressure (C-p) of a molecular liquid medium is not only a basic physical prop erty applicable in the calculation of microscopic characteristics but also a cru cial property in chemical engineering processes. In this work, we utilized machi ne learning (ML) methodologies based on an established molecular liquid database to develop predictive models for C-p of fluids.” Funders for this research include Project of Stable Support for a Youth Team in a Basic Research Field, Chinese Academy of Sciences, Science and Technology Rese arch and Development Plan Joint Foundation of Henan Province, Beijing Municipal Science & Technology Commission.
      原文链接:
    • NETL
    • NSTL

    Researcher from China University of Geosciences Discusses Findings in Machine Le arning (Landslide Recognition Based on Machine Learning Considering Terrain Feat ure Fusion)

    55-56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 originating from Wuhan, People’s Republ ic of China, by NewsRx correspondents, research stated, “Landslides are one of t he major disasters that exist worldwide, posing a serious threat to human life a nd property safety. Rapid and accurate detection and mapping of landslides are c rucial for risk assessment and humanitarian assistance in affected areas.” Financial supporters for this research include National Natural Science Foundati on of China. The news reporters obtained a quote from the research from China University of G eosciences: “To achieve this goal, this study proposes a landslide recognition m ethod based on machine learning (ML) and terrain feature fusion. Taking the Dawa n River Basin in Detuo Township and Tianwan Yi Ethnic Township as the research a rea, firstly, landslide-related data were compiled, including a landslide invent ory based on field surveys, satellite images, historical data, high-resolution r emote sensing images, and terrain data. Then, different training datasets for la ndslide recognition are constructed, including full feature datasets that fusion terrain features and remote sensing features and datasets that only contain rem ote sensing features. At the same time, different ratios of landslide to non-lan dslide (or positive/negative, P/N) samples are set in the training data. Subsequ ently, five ML algorithms, including Extreme Gradient Boost (XGBoost), Adaptive Boost (AdaBoost), Light Gradient Boost (LightGBM), Random Forest (RF), and Convo lutional Neural Network (CNN), were used to train each training dataset, and lan dslide recognition was performed on the validation area. Finally, accuracy (A), precision (P), recall ® F1 score (F1), and intersection over union (IOU) were s elected to evaluate the landslide recognition ability of different models. The r esearch results indicate that selecting ML models suitable for the study area an d the ratio of the P/N samples can improve the A, R, F1, and IOU of landslide id entification results, resulting in more accurate and reasonable landslide identi fication results; Fusion terrain features can make the model recognize landslide s more comprehensively and align better with the actual conditions. The best-per forming model in the study is LightGBM.”
      原文链接:
    • NETL
    • NSTL

    Universidad Politecnica de Madrid Reports Findings in Machine Learning (FRELSA: A dataset for frailty in elderly people originated from ELSA and evaluated throu gh machine learning models)

    56-57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 Machine Learning is th e subject of a report. According to news originating from Madrid, Spain, by News Rx correspondents, research stated, “Frailty is an age-related syndrome characte rized by loss of strength and exhaustion and associated with multi-morbidity. Ea rly detection and prediction of the appearance of frailty could help older peopl e age better and prevent them from needing invasive and expensive treatments.” Our news journalists obtained a quote from the research from Universidad Politec nica de Madrid, “Machine learning techniques show promising results in creating a medical support tool for such a task. This study aims to create a dataset for machine learning-based frailty studies, using Fried’s Frailty Phenotype definiti on. Starting from a longitudinal study on aging in the UK population, we defined a frailty label for each subject. We evaluated the definition by training seven different models for detecting frailty with data that were contemporary to the ones used for the definition. We then integrated more data from two years before to obtain prediction models with a 24-month horizon. Features selection was per formed using the MultiSURF algorithm, which ranks all features in order of relev ance to the detection or prediction task. We present a new frailty dataset of 53 03 subjects and more than 6500 available features. It is publicly available, pro vided one has access to the original English Longitudinal Study of Ageing datase t. The dataset is balanced after grouping frailty with pre-frailty, and it is su itable for multiclass or binary classification and prediction problems. The seve n tested architectures performed similarly, forming a solid baseline that can be improved with future work. Linear regression achieved the best F-score and AURO C in detection and prediction tasks. Creating new frailty-annotated datasets of this size is necessary to develop and improve the frailty prediction techniques. We have shown that our dataset can be used to study and test machine learning m odels to detect and predict frailty.”
      原文链接:
    • NETL
    • NSTL

    Data on Support Vector Machines Reported by Researchers at Ludong University (Ts vm: Transfer Support Vector Machine for Predicting Mpra Validated Regulatory Var iants)

    57-57页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Support Vector Machines. According to news reporting originating from Shandong, People’ s Republic of China, by NewsRx correspondents, research stated, “Genome-wide ass ociation studies have shown that common genetic variants associated with complex diseases are mostly located in non-coding regions, which may not be causal. In addition, the limited number of validated non-coding functional variants makes i t difficult to develop an effective supervised learning model.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news editors obtained a quote from the research from Ludong University, “The refore, improving the accuracy of predicting non-coding causal variants has beco me critical. This study aims to build a transfer learning-based machine learning method for predicting regulatory variants to overcome the problem of limited sa mple size. This paper presents a supervised learning method transfer support vec tor machine (TSVM) for massively parallel reporter assays (MPRA) validated regul atory variants prediction. First, uses a convolutional neural network to extract features with transfer learning. Second, the extracted features are selected by random forest method. Third, the selected features are used to train support ve ctor machine for classification. We performed scale sensitivity experiments on t he MPRA dataset and validated the effectiveness of transfer learning.”
      原文链接:
    • NETL
    • NSTL