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

    New Artificial Intelligence Study Findings Have Been Published by Researchers at South China Normal University (What are the differences? A comparative study of generative artificial intelligence translation and human translation of scienti fic ...)

    48-49页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on artificial intelligence is now available. According to news originating from South China Normal Univers ity by NewsRx editors, the research stated, "Generative artificial intelligence translation (GenAIT) brings convenience yet also imposes severe challenges on th e dissemination of knowledge. The respective (dis)advantages of GenAIT and human translation (HT), and the ways to promote their effective interaction have not been sufficiently explored yet." Our news editors obtained a quote from the research from South China Normal Univ ersity: "This study investigates the linguistic features of GenAIT and HT of sci entific texts rendered from English to Chinese from lexical and syntactic levels . The GenAIT is generated by ChatGPT 3.5, a representative GenAI platform, while HTs are done by 19 Master-of-Translation-and-Interpreting students in China. Da ta shows that GenAIT and HTs present distinguished linguistic features in both l evels. At the lexical level, HT exhibits lengthier texts with a lower average wo rd diversity; GenAIT presents higher accuracy in translating terminology. At the syntactic level, the average sentence count in HT is greater, whereas its avera ge sentence length measured in tokens is shorter. Moreover, human translators te nd to transform sentences from passive voice into active voice more frequently t han ChatGPT 3.5 does. Furthermore,human translators exhibit superior skills in deconstructing lengthy and complex sentences into shorter, more comprehensible c lauses."

    Zhejiang Normal University Reports Findings in Liver Metastasis (Rapid detection of liver metastasis risk in colorectal cancer patients through blood test indic ators)

    49-50页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Liver Metas tasis is the subject of a report. According to news originating from Jinhua, Peo ple's Republic of China, by NewsRx correspondents, research stated, "Colorectal cancer (CRC) is one of the most common malignancies, with liver metastasis being its most common form of metastasis. The diagnosis of colorectal cancer liver me tastasis (CRCLM) mainly relies on imaging techniques and puncture biopsy techniq ues, but there is no simple and quick early diagnosisof CRCLM." Our news journalists obtained a quote from the research from Zhejiang Normal Uni versity, "This study aims to develop a method for rapidly detecting the risk of liver metastasis in CRC patients through blood test indicators based on machine learning (ML) techniques, thereby improving treatment outcomes. To achieve this, blood test indicators from 246 CRC patients and 256 CRCLM patients were collect ed and analyzed, including routine blood tests, liver function tests, electrolyt e tests, renal function tests, glucose determination, cardiac enzyme profiles, b lood lipids, and tumor markers. Six commonly used ML models were used for CRC an d CRCLM classification and optimized by using a feature selection strategy. The results showed that AdaBoost algorithm can achieve the highest accuracy of 89.3% among the six models, which improved to 91.1% after feature select ion strategy, resulting with 20 key markers."

    Data on Robotics Discussed by Researchers at Qingdao University (Fuzzy Observer- based Command Filtered Adaptive Control of Flexible Joint Robots With Time-varyi ng Output Constraints)

    50-51页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Robotic s. According to news reporting originating from Qingdao, People's Republic of Ch ina, by NewsRx correspondents, research stated, "Flexible joint robots (FJR) sys tems are used in many aspects of actual production due to its high compliance, l ow energy consumption, human-computer interaction safety and other characteristi cs. A fuzzy observer-based command filtered adaptive control method is applied t o make FJR systems with time-varying output constraints (TVOC) and model uncerta inties operate safely in a complex environment in this brief." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Program for Changjiang Scholars & Innovative R esearch Team in University (PCSIRT), Major Innovation Project of Shandong Provin ce, Taishan Scholar Special Project Fund, Qingdao Key Technology Research and In dustrialization Demonstration Project.

    Researchers at Imperial College London Report New Data on Robotics (Benchmarking and Simulating Bimanual Robot Shoe Lacing)

    51-51页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ro botics. According to news reporting from London, United Kingdom, by NewsRx journ alists, research stated, "Manipulation of deformable objects is a challenging do main in robotics. Although it has been gaining attention in recent years, long-h orizon deformable object manipulation remains largely unexplored." Financial supporters for this research include UKRI under Grant, RAEng Chair in Emerging Technologies. The news correspondents obtained a quote from the research from Imperial College London, "In this letter, we propose a benchmark for the bi-manual Shoe Lacing ( SL) task for evaluating and comparing long-horizon deformable object manipulatio n algorithms. SL is a difficult sensorimotor task in everyday life as well as th e shoe manufacturing sector. Due to the complexity of the shoe structure, SL nat urally requires sophisticated long-term planning. We provide a rigorous definiti on of the task and protocols to ensure the repeatability of SL experiments. We p resent 6 benchmark metrics for quantitatively measuring the ecological validity of approaches towards bi-manual SL. We further provide an open-source simulation environment for training and testing SL algorithms, as well as details of the c onstruction and usage of the environment."

    Researcher at Shanghai Jiao Tong University Describes Research in Robotics (Moti on Planning for a Legged Robot with Dynamic Characteristics)

    52-53页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-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 Shanghai, People's Republic of China , by NewsRx correspondents, research stated, "Legged soccer robots present a sig nificant challenge in robotics owing to the need for seamless integration of per ception, manipulation, and dynamic movement." Financial supporters for this research include National Natural Science Foundati on of China; Startup Fund For Young Faculty At Sjtu.

    Zhejiang University Reports Findings in Robotics (Protocol for developing an exp losion-propeller hybrid driving underwater robot for AI-based concrete overhaul in real marine environments)

    52-52页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-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 originating from Zhejiang, People's Republic of China, by NewsRx correspondents, research stated, "We recently developed an exp losion-propeller hybrid driving underwater robot combined with an AI-based concr ete damage detection technique for concrete overhaul in real marine environments . Here, we describe steps for establishing a detection dataset, optimizing and t esting the algorithm, and preparing the explosive module." Our news journalists obtained a quote from the research from Zhejiang University , "We detail procedures for setting up the robot body, assembling, and preparing other tools. Finally, we outline steps for testing in the designated sea area, collecting data, and processing and analysis."

    University of Florence Reports Findings in COVID-19 (Genetic Algorithms for Feat ure Selection in the Classification of COVID-19 Patients)

    53-54页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Coronavirus - COVID-19 is the sub ject of a report. According to news reporting from Florence, Italy, by NewsRx jo urnalists, research stated, "Severe Acute Respiratory Syndrome CoronaVirus-2 (SA RS-CoV-2) infection can cause feared consequences, such as affecting microcircul atory activity. The combined use of HRV analysis, genetic algorithms, and machin e learning classifiers can be helpful in better understanding the characteristic s of microcirculation that are mainly affected by COVID-19 infection." Financial supporters for this research include Regione Toscana, Italy, European Research Council. The news correspondents obtained a quote from the research from the University o f Florence, "This study aimed to verify the presence of microcirculation alterat ions in patients with COVID-19 infection, performing Heart Rate Variability (HRV ) parameters analysis extracted from PhotoPlethysmoGraphy (PPG) signals. The dat aset included 97 subjects divided into two groups: healthy (50 subjects) and pat ients affected by mild-severity COVID-19 (47 subjects). A total of 26 parameters were extracted by the HRV analysis and were investigated using genetic algorith ms with three different subject selection methods and five different machine lea rning classifiers. Three parameters: meanRR, alpha1, and sd2/sd1 were considered significant, combining the results obtained by the genetic algorithm. Finally, machine learning classifications were performed by training classifiers with onl y those three features. The best result was achieved by the binary Decision Tree classifier, achieving accuracy of 82%, specificity (or precision) of 86 %, and sensitivity of 79%."

    Peking University First Hospital Reports Findings in Robotics (Totally Intracorp oreal Robot-Assisted Bilateral Ileal Ureter Replacement for the Treat-ment of Ur eteral Strictures using Kangduo Surgical Robot 2000 Plus)

    54-55页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-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 Beijing, People's Republic of China, by NewsRx editors, research stated, "Ureteroplasty using buccal or lingua l mucosa graft Is feasible for complex proximal ureteral stricture (1, 2). Ileal ureter replacement is considered as the last resort for ureteral reconstruction ." Our news journalists obtained a quote from the research from Peking University F irst Hospital, "Totally intracorporeal robot-assisted ileal ureter replacement c an be performed safely and effectively (3). In China, the KangDuo Surgical Robot 2000 Plus (KD-SR-2000 Plus) has been developed featuring two surgeon consoles a nd five robotic arms. This study aims to share our experience with totally intra corporeal robot-assisted bilateral ileal ureter replacement using KD-SR-2000 Plu s. A 59-year-old female patient underwent a complete intracorporeal robot-assist ed bilateral ileal ureter replacement for the treatment of ureteral strictures u sing KD-SR-2000 Plus. The surgical procedure involved dissecting the proximal en ds of the bilateral ureteral strictures, harvesting the ileal ureter, restoring intestinal continuity, and performing an anastomosis between the ileum and the u reteral end as well as the bladder. The data were prospectively collected and an alyzed. The surgery was successfully completed with single docking without open conversion. The length of the harvested ileal ureter was 25 cm. The docking time , operation time and console time were 3.4 min., 271 min and 231 min respectivel y. The estimated blood loss was 50 mL. The postoperative hospitalization was 6 d ays. No perioperative complications occurred. It is technically feasible to perf orm totally intracorporeal robot-assisted bilateral ileal ureter replacement for the treatment of ureteral strictures using KD-SR-2000 Plus."

    New Findings Reported from Jadavpur University Describe Advances in Machine Lear ning (Contextual Authentication of Users and Devices Using Machine Learning)

    55-56页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on Machine Learning have been presented. According to news reporting originating from Kolkata, India, by NewsRx correspondents, research stated, "At the time of authentication, confide ntial data are exchanged between the user/device and the authentication server t o determine the legitimacy of the source requesting authentication. Safeguarding the authentication process from security attacks is of utmost importance, and v arious authentication methods exist depending on the system's requirements." Our news editors obtained a quote from the research from Jadavpur University, "H owever, no authentication process can guarantee full-proof security. This resear ch aimed to use the context of users and devices during authentication to detect anomalies and security-related attacks. In particular, denial-ofservice (DoS)/ distributed denial-of-service (DDoS) attacks and brute-force attacks have been a nalyzed in detail using contextual information. Extensive simulations were condu cted on the benchmark CICIDS2017 dataset using the Weka tool. The performance m etrics of recall, precision, accuracy, f-score, and model-built time were comput ed for the four machine-learning classifiers-J48, Random Forest, Multi-Layer Per ceptron, and Bayes Net-for different combinations of data splits and groups of d ata features. For both DoS/DDoS and brute-force attacks, some of the experimenta l results show a more than 99% value for recall, precision, accura cy, and f-score."

    Zhejiang Normal University Researchers Reveal New Findings on Machine Learning ( Optimized quantum LSTM using modified electric Eel foraging optimization for rea l-world intelligence engineering systems)

    56-57页
    查看更多>>摘要:2024 OCT 03 (NewsRx)-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 Jinhua, Pe ople's Republic of China, by NewsRx correspondents, research stated, "The integr ation of metaheuristics with machine learning methodologies presents significant advantages, particularly in optimization and computational intelligence. This a malgamation leverages the global search capabilities of metaheuristics alongside the pattern recognition and predictive prowess of machine learning, facilitatin g enhanced convergence rates and solution quality in complex problem spaces." Funders for this research include King Saud University. Our news correspondents obtained a quote from the research from Zhejiang Normal University: "The Quantum Long Short-Term Memory (QLSTM) emerges as a highly effi cient deep learning model tailored to tackle such intricate engineering problems . The QLSTM's architecture, comprising data encoding, variational, and quantum m easurement layers, facilitates the effective encoding and processing of civil en gineering data, leading to heightened prediction accuracy. However, the task of determining optimal values for QLSTM parameters presents challenges due to its N P-problem nature and time-consuming characteristics. To address this, we propose an alternative technique to optimize the QLSTM based on a modified Electric Eel Foraging Optimization (MEEFO). The MEEFO is a modified version of the original EEFO that applies triangular mutation operators to boost the search capability o f the traditional EEFO. Thus, the MEEFO optimizes the QLSTM and boosts its predi ction performance."