期刊,Robotics & Machine Learning Daily News 2024年卷Mar.11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

Research on Robotics Published by a Researcher at Beijing Forestry University (A Multiple Criteria Decision-Making Method Generated by the Space Colonization Al gorithm for Automated Pruning Strategies of Trees)

10-11页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on robotics is the subject of a new report. According to news reporting originating from Beijing, People's Republic of China, by NewsRx correspondents, research stated, "The rise of mechanical aut omation in orchards has sparked research interest in developing robots capable o f autonomous tree pruning operations. To achieve accurate pruning outcomes, thes e robots require robust perception systems that can reconstruct three-dimensiona l tree characteristics and execute appropriate pruning strategies." Funders for this research include Contract Research of Non-government Funded Pro jects. The news editors obtained a quote from the research from Beijing Forestry Univer sity: "Threedimensional modeling plays a crucial role in enabling accurate prun ing outcomes. This paper introduces a specialized tree modeling approach using t he space colonization algorithm (SCA) tailored for pruning. The proposed method extends SCA to operate in three-dimensional space, generating comprehensive cher ry tree models. The resulting models are exported as normalized point cloud data , serving as the input dataset. Multiple criteria decision analysis is utilized to guide pruning decisions, incorporating various factors such as tree species, tree life cycle stages, and pruning strategies during real-world implementation. The pruning task is transformed into a point cloud neural network segmentation task, identifying the trunks and branches to be pruned. This approach reduces th e data acquisition time and labor costs during development. Meanwhile, pruning t raining in a virtual environment is an application of digital twin technology, w hich makes it possible to combine the meta-universe with the automated pruning o f fruit trees. Experimental results demonstrate superior performance compared to other pruning systems."

原文链接:

NETL
NSTL

New Findings in Computational Intelligence Described from University of Tokyo (D evelopment and Practical Applications of Computational Intelligence Technology)

11-12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 computational intellig ence is the subject of a new report. According to news originating from Tokyo, J apan, by NewsRx correspondents, research stated, "Computational intelligence (CI ) uses applied computational methods for problem-solving inspired by the behavio r of humans and animals. Biological systems are used to construct software to so lve complex problems, and one type of such system is an artificial immune system (AIS), which imitates the immune system of a living body." Our news correspondents obtained a quote from the research from University of To kyo: "AISs have been used to solve problems that require identification and lear ning, such as computer virus identification and removal, image identification, a nd function optimization problems. In the body's immune system, a wide variety o f cells work together to distinguish between the self and non-self and to elimin ate the non-self. AISs enable learning and discrimination by imitating part or a ll of the mechanisms of a living body's immune system. Certainly, some deep neur al networks have exceptional performance that far surpasses that of humans in ce rtain tasks, but to build such a network, a huge amount of data is first require d. These networks are used in a wide range of applications, such as extracting k nowledge from a large amount of data, learning from past actions, and creating t he optimal solution (the optimization problem). A new technique for pre-training natural language processing (NLP) software ver.9.1by using transformers called Bidirectional Encoder Representations (BERT) builds on recent research in pre-tr aining contextual representations, including Semi-Supervised Sequence Learning, Generative Pre-Training, ELMo (Embeddings from Language Models), which is a meth od for obtaining distributed representations that consider context, and ULMFit ( Universal Language Model Fine-Tuning). BERT is a method that can address the iss ue of the need for large amounts of data, which is inherent in large-scale model s, by using pre-learning with unlabeled data. An optimization problem involves " finding a solution that maximizes or minimizes an objective function under given constraints". In recent years, machine learning approaches that consider patter n recognition as an optimization problem have become popular. This pattern recog nition is an operation that associates patterns observed as spatial and temporal changes in signals with classes to which they belong."

原文链接:

NETL
NSTL

University of Louisville School of Medicine Reports Findings in Urinary Diversio n (Identify risk factors for perioperative outcomes in Intracorporeal Urinary Di version and Extracorporeal Urinary Diversion with Robotic Cystectomy)

12-13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 Surgery - Urinary Dive rsion is the subject of a report. According to news originating from Louisville, Kentucky, by NewsRx correspondents, research stated, "The increasing adoption o f robotic-assisted cystectomy with intracorporeal urinary diversion (ICUD), desp ite its complexity, prompts a detailed comparison with extracorporeal urinary di version (ECUD). Our study at a single institution investigates perioperative out comes and identifies risk factors impacting the success of these surgical approa ches." Our news journalists obtained a quote from the research from the University of L ouisville School of Medicine, "In this retrospective analysis, 174 patients who underwent robotic-assisted cystectomy at the University of Louisville from June 2016 to August 2021 were reviewed. The cohort was divided into two groups based on the urinary diversion method: 30 patients underwent ECUD and 144 underwent IC UD. Data on demographics, complication rates, length of hospital stay, and readm ission rates were meticulously collected and analyzed. Operative times were comp arable between the ICUD and ECUD groups. However, the ICUD group had a significa ntly lower intraoperative transfusion rate (0.5 vs. 1.0, p=0.02) and shorter hos pital stay (7.8 vs. 12.3 days, p<0.001). Factors such as ma le sex, smoking history, diabetes mellitus, intravesical therapy, higher ASA, an d ACCI scores were associated with increased Clavien-Dindo Grade 3 or higher com plications. Age over 70 was the sole factor linked to a higher 90-day readmissio n rate, with no specific characteristics influencing the 30-day rate. Robotic cy stectomy with ICUD results in shorter hospitalizations and lower intraoperative transfusion rates compared to ECUD, without differences in operative time, high- grade postoperative complications, or readmission rates."

原文链接:

NETL
NSTL

Findings in Intelligent and Connected Vehicles Reported from Tokyo Institute of Technology (Scale variant vehicle object recognition by CNN module of multi-pool ing-PCA process)

13-14页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Research findings on intelligent and connected ve hicles are discussed in a new report. According to news reporting out of Tokyo, Japan, by NewsRx editors, research stated, "The moving vehicles present differen t scales in the image due to the perspective effect of different viewpoint dista nces." Funders for this research include National Natural Science Foundation of China. The news reporters obtained a quote from the research from Tokyo Institute of Te chnology: "The premise of advanced driver assistance system (ADAS) system for sa fety surveillance and safe driving is early identification of vehicle targets in front of the ego vehicle. The recognition of the same vehicle at different scal es requires feature learning with scale invariance. Unlike existing feature vect or methods, the normalized PCA eigenvalues calculated from feature maps are used to extract scale-invariant features. This study proposed a convolutional neural network (CNN) structure embedded with the module of multipooling- PCA for scale variant object recognition. The validation of the proposed network structure is verified by scale variant vehicle image dataset. Compared with scale invariant network algorithms of Scaleinvariant feature transform (SIFT) and FSAF as well as miscellaneous networks, the proposed network can achieve the best recognition accuracy tested by the vehicle scale variant dataset."

原文链接:

NETL
NSTL

Sichuan University Reports Findings in Upper Extremity Deep Vein Thrombosis (Per ipherally inserted central-related upper extremity deep vein thrombosis and mach ine learning)

14-15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 Cardiovascular Disease s and Conditions - Upper Extremity Deep Vein Thrombosis is the subject of a repo rt. According to news originating from Chengdu, People's Republic of China, by N ewsRx correspondents, research stated, "To establish a prediction model of upper extremity deep vein thrombosis (UEDVT) associated with peripherally inserted ce ntral catheter (PICC) based on machine learning (ML), and evaluate the effect. 4 52 patients with malignant tumors who underwent PICC implantation in West China Hospital from April 2021 to December 2021 were selected through convenient sampl ing." Our news journalists obtained a quote from the research from Sichuan University, "UEDVT was detected by ultrasound. Machine learning models were established usi ng the least absolute contraction and selection operator (LASSO) regression algo rithm: Seeley scale model (ML-Seeley-LASSO) and ML model. The information of pat ients with and without UEDVT was randomly allocated to the training set and test set of the two models, and the prediction effect of machine learning and existi ng prediction tools was compared. Machine learning training set and test set wer e better than Seeley evaluation results, and MLSeeley- LASSO performance in trai ning set was better than ML-LASSO. The performance of ML-LASSO in the test set i s better than that of ML-Seeley-LASSO. The use of ML model (ML-LASSO and MLSeel ey-LASSO) in PICC-related UEDVT shows good effectiveness (the area under the sub ject's working characteristic curve is 0.856, 0.799), which is superior to the c urrently used Seeley assessment tool."

原文链接:

NETL
NSTL

Endicott College Reports Findings in Artificial Intelligence (Starting the Conve rsation Around the Ethical Use of Artificial Intelligence in Applied Behavior An alysis)

15-16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 Artificial Intelligenc e is the subject of a report. According to news reporting from Beverly, Massachu setts, by NewsRx journalists, research stated, "Artificial intelligence (AI) is increasingly a part of our everyday lives. Though much AI work in healthcare has been outside of applied behavior analysis (ABA), researchers within ABA have be gun to demonstrate many different ways that AI might improve the delivery of ABA services." The news correspondents obtained a quote from the research from Endicott College , "Though AI offers many exciting advances, absent from the behavior analytic li terature thus far is conversation around ethical considerations when developing, building, and deploying AI technologies. Further, though AI is already in the p rocess of coming to ABA, it is unknown the extent to which behavior analytic pra ctitioners are familiar (and comfortable) with the use of AI in ABA. The purpose of this article is twofold. First, to describe how existing ethical publication s (e.g., BACB Code of Ethics) do and do not speak to the unique ethical concerns with deploying AI in everyday, ABA service delivery settings. Second, to raise questions for consideration that might inform future ethical guidelines when dev eloping and using AI in ABA service delivery."

原文链接:

NETL
NSTL

Data on Androids Detailed by Researchers at Center for Research and Advanced Stu dies of the National Polytechnic Institute (CINVESTAV) (Humanoid Trajectory Opti mization With B-splines and Analytical Centroidal Momentum Derivatives)

16-16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 - An droids have been published. According to news reporting from Saltillo, Mexico, b y NewsRx journalists, research stated, "This paper presents efficient geometric algorithms to analytically evaluate the first- and second-order information of h umanoid dynamics within a trajectory optimization scheme. In particular, the exa ct Hessians of the robot's center of mass and the centroidal momentum are provid ed to the optimization solver for synthesizing dynamically feasible humanoid mot ions." The news correspondents obtained a quote from the research from the Center for R esearch and Advanced Studies of the National Polytechnic Institute (CINVESTAV), "The transcription method applies direct collocation to parametrize the humanoid 's configuration space with B-Spline curves. The proposed algorithms avoid the c omputation of redundant information by exploiting the commutativity of the Krone cker product and the symmetry in second-order derivatives."

原文链接:

NETL
NSTL

Findings in Machine Learning Reported from King Khalid University (Machine learn ing framework for simulation of artifacts in paranasal sinuses diagnosis using C T images)

17-18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 Abha, Saudi Arabia, by NewsRx editors, the research stated, "In the medical field, diagnostic tools th at make use of deep neural networks have reached a level of performance never be fore seen. A proper diagnosis of a patient's condition is crucial in modern medi cine since it determines whether or not the patient will receive the care they n eed." Our news journalists obtained a quote from the research from King Khalid Univers ity: "Data from a sinus CT scan is uploaded to a computer and displayed on a hig h-definition monitor to give the surgeon a clear anatomical orientation before e ndoscopic sinus surgery. In this study, a unique method is presented for detecti ng and diagnosing paranasal sinus disorders using machine learning. The research ers behind the current study designed their own approach. To speed up diagnosis, one of the primary goals of our study is to create an algorithm that can accura tely evaluate the paranasal sinuses in CT scans. The proposed technology makes i t feasible to automatically cut down on the number of CT scan images that requir e investigators to manually search through them all. In addition, the approach o ffers an automatic segmentation that may be used to locate the paranasal sinus r egion and crop it accordingly. As a result, the suggested method dramatically re duces the amount of data that is necessary during the training phase. As a resul t, this results in an increase in the efficiency of the computer while retaining a high degree of performance accuracy."

原文链接:

NETL
NSTL

Federal Scientific Agroengineering Center VIM Researchers Publish New Data on Ro botics (Multifunctional Robotic Device with Intelligent Positioning System)

17-17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 robotics have bee n published. According to news originating from the Federal Scientific Agroengin eering Center VIM by NewsRx editors, the research stated, "At the present stage of agricultural production development, Smart farming is widely used as a system atic transition from managing a separate technological operation to managing pro cesses that ensure the achievement of the required level of overall profitabilit y of production through the use of new decision-making tools and automated manag ement technologies." The news journalists obtained a quote from the research from Federal Scientific Agroengineering Center VIM: "This approach involves expanding the scope of machi nes, equipment and software, including the widespread use of robotic tools in ho rticultural production and processing technologies, in order to increase product ion efficiency, eliminate the ‘human factor' in the production of products, repl ace human participation in production processes with a large proportion of heavy manual labor and minimize harmful effects chemical protection products for huma ns and the environment. Another reason for the intensification of the developmen t and implementation of robotic tools with intelligent control systems in agricu lture is the shortage of technologists and engineers in farms, due to the unattr activeness of labor in the agro-industrial complex. The article discusses the is sues of increasing the efficiency of industrial gardening, through the developme nt and implementation of robotic systems and electric drive transformer modules in various technological processes. The features of the designs and practical ap plication of robots with intelligent motion control systems on garden plantation s are analyzed."

原文链接:

NETL
NSTL

Study Findings on Robotics Discussed by Researchers at University of Bologna (Fo rce-Sensor-Free Implementation of a Hybrid Position-Force Control for Overconstr ained Cable-Driven Parallel Robots)

18-19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 from Bologna, Ita ly, by NewsRx correspondents, research stated, "This paper proposes a hybrid pos ition-force control strategy for overconstrained cable-driven parallel robots (C DPRs)." Our news reporters obtained a quote from the research from University of Bologna : "Overconstrained CDPRs have more cables (* * m* * ) than degrees of freedom (* * n* * ), and the idea of the proposed controller is to control * * n* * cables in length and the other m - n ones in force. Two controller implementations are developed, one using the motor torque and one using the motor following-error i n the feedback loop for cable force control. A friction model of the robot kinem atic chain is introduced to improve the accuracy of the cable force estimation. Compared to similar approaches available in the literature, the novelty of the p roposed control strategy is that it does not rely on force sensors, which reduce s the hardware complexity and cost. The developed control scheme is compared to classical methods that exploit force sensors and to a pure inverse kinematic con troller. The experimental results show that the new controller provides good tra cking of the desired cable forces, maintaining them within the given bounds."

原文链接:

NETL
NSTL