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 reporting out of Changsha, People's Rep ublic of China, by NewsRx editors, research stated, "Full-thickness macular hole (FTMH) leads to central vision loss. It is essential to identify patients with FTMH at high risk of postoperative failure accurately to achieve anatomical clos ure." Our news journalists obtained a quote from the research from the Second Xiangya Hospital of Central South University, "This study aimed to construct a predictiv e model for the anatomical outcome of FTMH after surgery. A retrospective study was performed, analyzing 200 eyes from 197 patients diagnosed with FTMH. Radiomi cs features were extracted from optical coherence tomography (OCT) images. Logis tic regression, support vector machine (SVM), and backpropagation neural network (BPNN) classifiers were trained and evaluated. Decision curve analysis and surv ival analysis were performed to assess the clinical implications. Sensitivity, s pecificity, F1 score, and area under the receiver operating characteristic curve (AUC) were calculated to assess the model effectiveness. In the training set, t he AUC values were 0.998, 0.988, and 0.995, respectively. In the test set, the A UC values were 0.941, 0.943, and 0.968, respectively. The OCT-omics scores were significantly higher in the ‘Open' group than in the ‘Closed' group and were pos itively correlated with the minimum diameter (MIN) and base diameter (BASE) of F TMH."
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-Hypertension is the subject of a report. According to news or iginating from Genk, Belgium, by NewsRx correspondents, research stated, "Arteri al hypertension is a major cause of mortality and morbidity worldwide. Medical t herapy is the most common treatment." Our news journalists obtained a quote from the research from the Department of U rology, "However, in some cases there is a persistent high blood pressure despit e medical therapy. These patients with medication refractory arterial hypertensi on can be treated by renal denervation. Until now an endovascular approach has b een used. There are however limitations in eligibility based on vascular or anat omical anomalies."
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 reporting out of Wenzhou, Peopl e's Republic of China, by NewsRx editors, research stated, "Data-driven artifici al intelligence models play an important role in mechanical fault diagnosis. Gen erally, it is difficult to collect relative complete fault samples, which limits the application of artificial intelligence models for complex mechanical system s." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Zhejiang Province Science and Technology Plan Project, Hebei Provincial Program on Key Basic Research Project, Wenzhou Major Science and Tec hnology Innovation Project of China.
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 Islamabad, Pakistan, b y NewsRx editors, the research stated, "With the rapid advancement in the manufa cturing industry, there has been a massive rise in the demand for products made of fiber reinforced polymer composites as they have high stiffness and strength to weight ratios." The news editors obtained a quote from the research from National University of Science and Technology (NUST): "They are widely used in the manufacturing of par ts in aerospace and automobile industry. The manual draping process of prepreg o n the mold is time intensive and requires a highly skilled worker to perform the task. Various techniques have been designed to automate the process of composit e parts manufacturing using automated fiber placement (AFP), automated tape layi ng (ATL) and automated plies layup. These methods use robots equipped with an en d effector designed to drape the prepreg. The system utilizes both single and mu lti-robot cells for the process of composites manufacturing. The aim of this pap er is to review the techniques and strategies employed for conforming and graspi ng of prepreg."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Researchers detail new data in artificial intelli gence. According to news originating from Gimhae, South Korea, by NewsRx corresp ondents, research stated, "One kind of autonomous vehicle that can take instruct ions from the driver by reading their electroencephalogram (EEG) signals using a Brain-Computer Interface (BCI) is called a Brain-Controlled Vehicle (BCV). The operation of such a vehicle is greatly affected by how well the BCI works." Our news reporters obtained a quote from the research from Inje University: "At present, there are limitations on the accuracy of BCI recognition, the number of distinguishable command categories, and the execution duration of command recog nition. Consequently, vehicles that are exclusively controlled by EEG signals de monstrate suboptimal control performance. To address the difficulty of improving the control capabilities of brain-controlled cars while maintaining BCI perform ance, a fuzzy logic-based technique called as Fuzzy Brain-Control Fusion Control is introduced. This approach uses Fuzzy Discrete Event System (FDES) supervisor y theory to verify the accuracy of the driver's brain-controlled directives. Con currently, a fuzzy logic-based automatic controller is developed to generate dec isions automatically in accordance with the present state of the vehicle via fuz zy reasoning. The final decision is then reached through the application of seco ndary fuzzy reasoning to the accuracy of the driver's instructions and the autom ated decisions to make adjustments that are more consistent with human intent."
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 Shanghai, People's Republic of China, by NewsRx editors, research stated, "Learning from demonstration (LfD) e nables robots to intuitively acquire new skills from human demonstrations and in crementally evolve robotic intelligence. Given the significance of LfD in a wide variety of applications, this survey aims to update the recently related develo pment from the perspective of the autonomous generation of robotic trajectories via LfD." Financial supporters for this research include Several research, internationally collaborative, and overseas PhD scholarship projects of the National Natural Sc ience Foundation of China, Science & Technology Commission of Shan ghai Municipality (STCSM), China Scholarship Council, Engineering & Physical Sciences Research Council (EPSRC), China Postdoctoral Science Foundation.
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 Milan, Italy, by NewsRx corresponden ts, research stated, "The use of laser beam welding with robotic manipulators is expanding towards wider industrial applications as the system availability incr eases with reduced capital costs. Conventionally, laser welding requires high po sitioning and coupling accuracy." Financial support for this research came from BLM Adige. Our news journalists obtained a quote from the research from Polytechnic Univers ity Milan, "Due to the variability in the part geometry and positioning, as well as the thermal deformation that may occur during the process, joint position an d fit-up are not always acceptable nor predictable a-priori if simple fixtures a re used. This makes the passage from virtual CAD/CAM environment to real product ion site not trivial, limiting applications where short part preparations are a need like small-batch productions. Solutions that render the laser welding opera tions feasible for production series with non-stringent tolerances are required to serve a wider range of industrial applications. Such solutions should be able to track the seam as well as tolerating variable gaps formed between the parts to be joined. In this work, an online correction for robot trajectory based on a greyscale coaxial vision system with external illumination and an adaptive wobb ling strategy are proposed as means to increase the overall flexibility of a man ufacturing plant. The underlying vision algorithm and control architectures are presented; the robustness of the system to poor illumination conditions and vari able reflection conditions is also discussed. The developed solution employed tw o control loops: the first is able to change the robot pose to follow varying tr ajectories; the second, able to vary the amplitude of circular wobbling as a fun ction of the gap formed in butt-joint welds. Demonstrator cases on butt-joint we lds with AISI 301 stainless steel with increased complexity were used to test th e efficacy of the solution. The system was successfully tested on 2 mm thick, pl anar stainless-steel sheets at a maximum welding speed of 25 mm/s and yielded a maximum positioning and yaw-orientation errors of respectively 0.325 mm and 4.5 degrees. Continuous welds could be achieved with up to 1 mm gaps and variable se am position with the developed control method."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Machine Learning is the subject o f a report. According to news reporting from Xi'an, People's Republic of China, by NewsRx journalists, research stated, "Aerobic Granular Sludge (AGS) has advan tages over Activated sludge (AS) but faces challenges with long granulation peri ods. In this study, a novel grey-box model is devised to optimize the cultivatio n of AGS to shorten the formation time." The news correspondents obtained a quote from the research from the Xi'an Univer sity of Architecture and Technology, "This model is based on an existing white-b ox model. The modeling process starts with the application of four sensitivity a nalysis methods to assess the 12 model metrics selected. Subsequently, 12 predic tion models were constructed by combining the six Machine learning (ML) algorith ms and integrated algorithms, with the best performance selected (R = 0.98). Fin ally, an AGS selection pressure planning model was designed in conjunction with a simulated annealing (SA) algorithm to guide AGS training. The results demonstr ate that AGS formation could be achieved within four days under the model's opti mal control."
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 Machine Learning-Computational Intelligence. According to news reporting origi nating in Chongqing, People's Republic of China, by NewsRx journalists, research stated, "This paper focuses on the event-triggered-based prescribed-time optima l consensus control issue for switched stochastic nonlinear multi-agent systems under switching topologies. Notably, the system stability may be affected owing to the change in information transmission channels between agents." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Graduate Scientific Research and Innovation Foundation of Ch ongqing.
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 new report. According to news reporting from University Pa rk, Pennsylvania, by NewsRx journalists, research stated, "Precise gamma-ray spe ctral analysis is crucial in high-stakes applications, such as nuclear security. " Financial supporters for this research include Defense Threat Reduction Agency; Sandia National Laboratories. Our news correspondents obtained a quote from the research from Pennsylvania Sta te University (Penn State): "Research efforts toward implementing machine learni ng (ML) approaches for accurate analysis are limited by the resemblance of the t raining data to the testing scenarios. The underlying spectral shape of syntheti c data may not perfectly reflect measured configurations, and measurement campai gns may be limited by resource constraints. Consequently, ML algorithms for isot ope identification must maintain accurate classification performance under domai n shifts between the training and testing data. To this end, four different clas sifiers (Ridge, Random Forest, Extreme Gradient Boosting, and Multilayer Percept ron) were trained on the same dataset and evaluated on twelve other datasets wit h varying standoff distances, shielding, and background configurations. A tailor ed statistical approach was introduced to quantify the similarity between the tr aining and testing configurations, which was then related to the predictive perf ormance."
NETL
NSTL