目的 提出双心室起搏室间间期（VV）优化新算法，并验证其合理性。 方法 选择2009年6月－2012年12月间在成都市第三人民医院心内科住院的慢性心力衰竭并接受双心室起搏是心脏再同步化治疗的患者41例，根据心脏电－机械耦联的原理，将体表心电图和超声指标的数量关系用新公式来表述，通过前瞻性自身对照研究来比较新算法与传统方法的差异。 结果 41例患者均分别采用新算法、传统超声法及腔内心电图法进行VV优化，测主动脉血流速度时间积分（AVTI）并统计耗时。经方差分析显示新算法的AVTI[（22.32 ± 3.48） cm]优于传统腔内心电图法的AVTI[（19.22 ± 3.07）cm]，组间差异有统计学意义（P＜0.05）；而新算法的耗时[（18.80 ± 3.30）min]较传统超声法的耗时[（203.81 ± 20.12）min]明显减少，组间差异有统计学意义（P＜0.01）。 结论 新算法用于双心室起搏是心脏再同步化治疗的VV优化准确、快速，具有合理性及临床推广价值。
Due to individual differences of the depth of anaesthesia (DOA) controlled objects, the drawbacks of monitoring index, the traditional PID controller of anesthesia depth could not meet the demands of nonlinear control. However, the adjustments of the rules of DOA fuzzy control often rely on personal experience and, therefore, it could not achieve the satisfactory control effects. The present research established a fuzzy closed-loop control system which takes the cerebral state index (CSI) value as a feedback controlled variable, and it also adopts the particle swarm optimization (PSO) to optimize the fuzzy control rule and membership functions between the change of CSI and propofol infusion rate. The system sets the CSI targets at 40 and 30 through the system simulation, and it also adds some Gaussian noise to imitate clinical disturbance. Experimental results indicated that this system could reach the set CSI point accurately, rapidly and stably, with no obvious perturbation in the presence of noise. The fuzzy controller based on CSI which has been optimized by PSO has better stability and robustness in the DOA closed loop control system.
Aiming at the disadvantages of traditional direct aperture optimization (DAO) method, such as slow convergence rate, prone to stagnation and weak global searching ability, a gradient-based direct aperture optimization (GDAO) is proposed. In this work, two different optimization methods are used to optimize the shapes and the weights of the apertures. Firstly, in order to improve the validity of the aperture shapes optimization of each search, the traditional simulated annealing (SA) algorithm is improved, the gradient is introduced to the algorithm. The shapes of the apertures are optimized by the gradient based SA method. At the same time, the constraints between the leaves of multileaf collimator (MLC) have been fully considered, the optimized aperture shapes are meeting the requirements of clinical radiation therapy. After that, the weights of the apertures are optimized by the limited-memory BFGS for bound-constrained (L-BFGS-B) algorithm, which is simple in calculation, fast in convergence rate, and suitable for solving large scale constrained optimization. Compared with the traditional SA algorithm, the time cost of this program decreased by 15.90%; the minimum dose for the planning target volume was improved by 0.29%, the highest dose for the planning target volume was reduced by 0.45%; the highest dose for the bladder and rectum, which are the organs at risk, decreased by 0.25% and 0.09%, respectively. The results of experiment show that the new algorithm can produce highly efficient treatment planning a short time and can be used in clinical practice.
Stress distribution of denture is an important criterion to evaluate the reasonableness of technological parameters, and the bite force derived from the antagonist is the critical load condition for the calculation of stress distribution. In order to improve the accuracy of stress distribution as much as possible, all-ceramic crown of the mandibular first molar with centric occlusion was taken as the research object, and a bite force loading method reflecting the actual occlusal situation was adopted. Firstly, raster scanning and three dimensional reconstruction of the occlusal surface of molars in the standard dental model were carried out. Meanwhile, the surface modeling of the bonding surface was carried out according to the preparation process. Secondly, the parametric occlusal analysis program was developed with the help of OFA function library, and the genetic algorithm was used to optimize the mandibular centric position. Finally, both the optimized case of the mesh model based on the results of occlusal optimization and the referenced case according to the cusp-fossa contact characteristics were designed. The stress distribution was analyzed and compared by using Abaqus software. The results showed that the genetic algorithm was suitable for solving the occlusal optimization problem. Compared with the reference case, the optimized case had smaller maximum stress and more uniform stress distribution characteristics. The proposed method further improves the stress accuracy of the prosthesis in the finite element model. Also, it provides a new idea for stress analysis of other joints in human body.
When performing eye movement pattern classification for different tasks, support vector machines are greatly affected by parameters. To address this problem, we propose an algorithm based on the improved whale algorithm to optimize support vector machines to enhance the performance of eye movement data classification. According to the characteristics of eye movement data, this study first extracts 57 features related to fixation and saccade, then uses the ReliefF algorithm for feature selection. To address the problems of low convergence accuracy and easy falling into local minima of the whale algorithm, we introduce inertia weights to balance local search and global search to accelerate the convergence speed of the algorithm and also use the differential variation strategy to increase individual diversity to jump out of local optimum. In this paper, experiments are conducted on eight test functions, and the results show that the improved whale algorithm has the best convergence accuracy and convergence speed. Finally, this paper applies the optimized support vector machine model of the improved whale algorithm to the task of classifying eye movement data in autism, and the experimental results on the public dataset show that the accuracy of the eye movement data classification of this paper is greatly improved compared with that of the traditional support vector machine method. Compared with the standard whale algorithm and other optimization algorithms, the optimized model proposed in this paper has higher recognition accuracy and provides a new idea and method for eye movement pattern recognition. In the future, eye movement data can be obtained by combining it with eye trackers to assist in medical diagnosis.
Emotion is a crucial physiological attribute in humans, and emotion recognition technology can significantly assist individuals in self-awareness. Addressing the challenge of significant differences in electroencephalogram (EEG) signals among different subjects, we introduce a novel mechanism in the traditional whale optimization algorithm (WOA) to expedite the optimization and convergence of the algorithm. Furthermore, the improved whale optimization algorithm (IWOA) was applied to search for the optimal training solution in the extreme learning machine (ELM) model, encompassing the best feature set, training parameters, and EEG channels. By testing 24 common EEG emotion features, we concluded that optimal EEG emotion features exhibited a certain level of specificity while also demonstrating some commonality among subjects. The proposed method achieved an average recognition accuracy of 92.19% in EEG emotion recognition, significantly reducing the manual tuning workload and offering higher accuracy with shorter training times compared to the control method. It outperformed existing methods, providing a superior performance and introducing a novel perspective for decoding EEG signals, thereby contributing to the field of emotion research from EEG signal.
Objective To analyze the risk factors of type 2 diabetes mellitus and establish BP neural network model for screening of type 2 diabetes mellitus based on particle swarm optimization (PSO) algorithm. Methods Inpatients with type 2 diabetes mellitus in the Department of Endocrinology of the Affiliated Hospital of Guangdong Medical University and the Second Affiliated Hospital of Guangdong Medical University between July 2021 and August 2022 were selected as the case group and healthy people in the Health Management Center of the Affiliated Hospital of Guangdong Medical University as the control group. Basic information and physical and laboratory examination indicators were collected for comparative analysis. PSO-BP neural network model, BP neural network model and logistic regression models were established using MATLAB R2021b software and the optimal screening model of type 2 diabetes mellitus was selected. Based on the optimal model, the mean impact value algorithm was used to screen the risk factors of type 2 diabetes mellitus. Results A total of 1 053 patients were included in the case group and 914 healthy peoples in the control group. Except for type of salt, family history of comorbidities, body mass index, total cholesterol, low density lipoprotein cholesterol and staple food intake (P>0.05), the other indexes showed significant differences between the two groups. The performance of the PSO-BP neural network model outperformed the BP neural network model and the logistic regression model. Based on PSO-BP neural network model, the mean impact value algorithm showed that the risk factors for type 2 diabetes mellitus were fasting blood glucose , heart rate, age , waist-arm ratio and marital status , and the protective factors for type 2 diabetes mellitus were high density lipoprotein cholestero, vegetable intake, residence, education level, fruit intake and meat intake. Conclusions There are many influencing factors of type 2 diabetes mellitus. Focus should be placed on high-risk groups and regular disease screening should be carried out to reduce the risk of type 2 diabetes. The screening model of PSO-BP neural network performs the best, and it can be extended to the early screening and diagnosis of other diseases in the future.