Objective Although robotic surgery adoption and its indications are growing worldwide,for multiple factors,including costs,there is a lack of training and experience.Our aim was to study the impact of a robotic introd...Objective Although robotic surgery adoption and its indications are growing worldwide,for multiple factors,including costs,there is a lack of training and experience.Our aim was to study the impact of a robotic introduction training program on gesture performance,such as suturing,in robot-naive individuals.Methods Using the DaVinci robot,a 2-hour program was based on virtual reality and anatomical model exercises.All participants performed 3 repetitions of virtual reality exercises on the virtual simulator,and then performed and were assessed on 2 tests,ie robot and laparoscopic training box.After the course,the participants were surveyed for this training program.Results Twenty-seven residents and surgeons were enrolled in the training program.With only 2 hours of training,all of the participants were able to complete the training program,thus learning generic and specific skills in robotic surgery.In virtual reality exercise,the scores of the 3 exercises increased significantly with every repetition(p<0.001)and the size of the increase was large.The completion time on the robot platform was 2.6 times faster(169.33±28.28 s vs.447.96±156.55 s,p<0.001)than that in the laparoscopic box,and the difference between both types of tests was large(pη2=0.797).The centralization and passage of the needle were significantly better on the robot platform(5 vs.3,p<0.001,r=0.47;5 vs.4,p<0.001,r=0.59)than in the laparoscopic box.For the intracorporeal stitch+knot test,every participant was able to perform the exercise on the robot but only 85.2%(23/27)in the laparoscopic box.Twenty-one participants answered the survey,and 13(61.9%)of them considered robotic performance independent of laparoscopic experience.Conclusions Surgeons are interested and seek training in robotic surgery.We implemented the first hands-on robotic surgery training program in Portugal and participants considered it was important and adequate for its purpose.All participants,even without robotic experience,learned quicker,performed better,faster and more precisely on the robot over laparoscopy.展开更多
In this study, we propose a hybrid AI optimal method to improve the efficiency of energy managementin a smart grid such as Renewable Energy Community. This method adopts a Time Delay Neural Networkto forecast the futu...In this study, we propose a hybrid AI optimal method to improve the efficiency of energy managementin a smart grid such as Renewable Energy Community. This method adopts a Time Delay Neural Networkto forecast the future values of the energy features in the community. Then, these forecasts are used by astochastic Model Predictive Control to optimize the community operations with a proper control strategy ofBattery Energy Storage System. The results of the predictions performed on a public dataset with a predictionhorizon of 24 h return a Mean Absolute Error of 1.60 kW, 2.15 kW, and 0.30 kW for photovoltaic generation,total energy consumption, and common services, respectively. The model predictive control fed with suchpredictions generates maximum income compared to the competitors. The total income is increased by 18.72%compared to utilizing the same management system without exploiting predictions from a forecasting method.展开更多
文摘Objective Although robotic surgery adoption and its indications are growing worldwide,for multiple factors,including costs,there is a lack of training and experience.Our aim was to study the impact of a robotic introduction training program on gesture performance,such as suturing,in robot-naive individuals.Methods Using the DaVinci robot,a 2-hour program was based on virtual reality and anatomical model exercises.All participants performed 3 repetitions of virtual reality exercises on the virtual simulator,and then performed and were assessed on 2 tests,ie robot and laparoscopic training box.After the course,the participants were surveyed for this training program.Results Twenty-seven residents and surgeons were enrolled in the training program.With only 2 hours of training,all of the participants were able to complete the training program,thus learning generic and specific skills in robotic surgery.In virtual reality exercise,the scores of the 3 exercises increased significantly with every repetition(p<0.001)and the size of the increase was large.The completion time on the robot platform was 2.6 times faster(169.33±28.28 s vs.447.96±156.55 s,p<0.001)than that in the laparoscopic box,and the difference between both types of tests was large(pη2=0.797).The centralization and passage of the needle were significantly better on the robot platform(5 vs.3,p<0.001,r=0.47;5 vs.4,p<0.001,r=0.59)than in the laparoscopic box.For the intracorporeal stitch+knot test,every participant was able to perform the exercise on the robot but only 85.2%(23/27)in the laparoscopic box.Twenty-one participants answered the survey,and 13(61.9%)of them considered robotic performance independent of laparoscopic experience.Conclusions Surgeons are interested and seek training in robotic surgery.We implemented the first hands-on robotic surgery training program in Portugal and participants considered it was important and adequate for its purpose.All participants,even without robotic experience,learned quicker,performed better,faster and more precisely on the robot over laparoscopy.
文摘In this study, we propose a hybrid AI optimal method to improve the efficiency of energy managementin a smart grid such as Renewable Energy Community. This method adopts a Time Delay Neural Networkto forecast the future values of the energy features in the community. Then, these forecasts are used by astochastic Model Predictive Control to optimize the community operations with a proper control strategy ofBattery Energy Storage System. The results of the predictions performed on a public dataset with a predictionhorizon of 24 h return a Mean Absolute Error of 1.60 kW, 2.15 kW, and 0.30 kW for photovoltaic generation,total energy consumption, and common services, respectively. The model predictive control fed with suchpredictions generates maximum income compared to the competitors. The total income is increased by 18.72%compared to utilizing the same management system without exploiting predictions from a forecasting method.
