RESUMO
Gesture recognition utilizes deep learning network model to automatically extract deep features of data; however, traditional machine learning algorithms rely on manual feature extraction and poor model generalization ability. In this paper, a multimodal gesture recognition algorithm based on convolutional long-term memory network is proposed. First, a convolutional neural network (CNN) is employed to automatically extract the deeply hidden features of multimodal gesture data. Then, a time series model is constructed using a long short-term memory (LSTM) network to learn the long-term dependence of multimodal gesture features on the time series. On this basis, the classification of multimodal gestures is realized by the SoftMax classifier. Finally, the method is experimented and evaluated on two dynamic gesture datasets, VIVA and NVGesture. Experimental results indicate that the accuracy rates of the proposed method on the VIVA and NVGesture datasets are 92.55% and 87.38%, respectively, and its recognition accuracy and convergence performance are better than those of other comparison algorithms.
Assuntos
Gestos , Memória de Curto Prazo , Algoritmos , Memória de Longo Prazo , Redes Neurais de ComputaçãoRESUMO
BACKGROUND: The shape and cross-sectional area (CSA) of internal jugular vein (IJV) are easily affected by external factors. That causes venous collapsibility. We tried to distend IJV by increasing the pressure on patients' abdomen in order to improve the success rate of internal jugular vein catheterization (IJVC). MATERIALS AND METHODS: Patients undergoing IJVC were randomly allocated to two groups: Group 1 and Group 2. For patients in Group 1, the pressure on abdomen was increased by placing a 3000 ml bag of normal saline (NS). No special treatment was arranged for patients in Group 2. Transverse images of right IJV were captured at the outer edge which was parallel to the cricoid by ultrasonography. CSA, circumference (CF), transverse diameter (TD) and anteroposterior diameter (APD) of right IJV were measured and compared. All patients underwent ultrasound-guided short-axis puncturing. The success rates of one-off puncturing in two groups were recorded and compared. RESULTS: The results under ultrasonography assessments show that CF, CSA, APD and success rate of puncturing in Group 1 were significantly higher than that of Group 2 (P < 0.05), while TD was not significantly increased (P > 0.05). There was no significant difference in complications between two groups (P > 0.05). CONCLUSION: Pressure on the abdomen could significantly increase CSA of IJV. That helps improving the success rate of one-off puncturing.
Assuntos
Cateterismo Venoso Central/métodos , Veias Jugulares/diagnóstico por imagem , Ultrassonografia de Intervenção/métodos , Cavidade Abdominal , Adulto , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pressão , Estudos Prospectivos , Punções , Método Simples-CegoRESUMO
BACKGROUND: Paravertebral block (PVB) as a sole anesthetic technique is difficult even in experienced hands. Hence, this study was undertaken to study the safety and efficacy of PVB and to compare with subarachnoid block (SAB) for inguinal hernia repair surgery (IHRS) in elderly male patients. MATERIALS AND METHODS: Sixty-five male patients aged 65 to 89 scheduled for IHRS were allocated randomly by computer-generated randomisation sequence into two groups. They underwent PVB (Group PVB: 33 patients were injected with 10â¯ml ropivacaine 0.5% at each level from T12 to L1) or SAB (Group SAB: 32 patients were injected with 15â¯mg ropivacaine 0.5% at L3-L4 level). Primary outcomes were hemodynamic changes and duration of postoperative analgesia. Secondary outcomes were dosage of remedial analgesics, time to perform the block, side effects and satisfaction of patients. RESULTS: The hemodynamics in the Group PVB were more stable than those in the Group SAB during surgery (Pâ¯<â¯0.05). The duration of post-operative analgesia was significantly longer in the Group PVB (Pâ¯<â¯0.001). The total dose of fentanyl was smaller in the Group PVB in the first 24â¯h (Pâ¯<â¯0.001). The time to perform the block was significantly longer in the Group PVB (Pâ¯<â¯0.001). There was a significant difference in the visual analogue scales (VAS) scores between the two groups at 4â¯h, 6â¯h, 8â¯h and 10â¯h (Pâ¯<â¯0.05) but not at 2â¯h, 12â¯h and 24â¯h (Pâ¯>â¯0.05). The VAS scores were lowest at 2â¯h for both the 2 groups, highest at 12â¯h for Group PVB and at 8â¯h for Group SAB respectively. The Group PVB had fewer adverse effects (Pâ¯<â¯0.05) and higher satisfaction of patients (Pâ¯<â¯0.05). CONCLUSION: Ultrasound-guided PVB can ensure the anesthetic effects of unilateral-opened IHRS in elderly male patients. It has a small impact on hemodynamics, a longer postoperative analgesia time and less complications.