Research on eye movement data classification using support vector machine with improved whale optimization algorithm / 生物医学工程学杂志

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.

Fully automatic volumetric modulated arc therapy planning based on dose prediction combined with an iterative optimization algorithm / 中华放射医学与防护杂志

Objective:To develope an automatic volumetric modulated arc therapy (VMAT) planning for rectal cancer based on a dose-prediction model for organs at risk(OARs) and an iterative optimization algorithm for objective parameter optimization.Methods:Totally 165 VMAT plans of rectal cancer patients treated in Peking University Cancer Hospital & Institute from June 2018 to January 2021 were selected to establish automatic VMAT planning. Among them, 145 cases were used for training the deep-learning model and 20 for evaluating the feasibility of the model by comparing the automatic planning with manual plans. The deep learning model was used to predict the essential dose-volume histogram (DVH) index as initial objective parameters(IOPs) and the iterative optimization algorithm can automatically modify the objective parameters according to the result of protocol-based automatic iterative optimization(PBAIO). With the predicted IOPs, the automatic planning model based on the iterative optimization algorithm was achieved using a program mable interface.Results:The IOPs of OARs of 20 cases were effectively predicted using the deep learning model, with no significantly statistical difference in the conformity index(CI) for planning target volume(PTV)and planning gross tumor volume(PGTV)between automatic and manual plans( P>0.05). The homogeneity index (HI) of PGTV in automatic and manual plans was 0.06 and 0.05, respectively( t=-6.92, P< 0.05). Compared with manual plans, the automatic plans significantly decreased the V30 for urinary bladder by 2.7% and decreased the V20 for femoral head sand auxiliary structure(avoidance)by 8.37% and 15.95%, respectively ( t=5.65, 11.24, P< 0.05). Meanwhile, the average doses to bladder, femoral heads, and avoidance decreased by 1.91, 4.01, and 3.88 Gy, respectively( t=9.29, 2.80, 10.23, P< 0.05) using the automatic plans. The time of automatic VMAT planning was (71.49±25.48)min in 20 cases. Conclusions:The proposed automatic planning based on dose prediction and an iterative optimization algorithm is feasible and has great potential for sparing OARs and improving the utilization rate of clinical resources.

Real Power Loss Reduction by Melon Fly Optimization and Spontaneous Process Algorithm's

Abstract In this work Melon Fly Optimization (MFO) Algorithm and Spontaneous Process Algorithm (SPA) is designed to reduce the Real power loss, voltage stability enhancement and reducing the Voltage deviation. In this work real power loss measured and how much loss has been reduced is also identified by suitable comparison with standard algorithms. In this society from common consumer to industry needs better quality of power continuously and constantly without much variation. One way to improve the quality of the power is to reduce the power loss. Also reduction of power loss will improve the economic conditions of the nation indirectly and it improves the productivity of the nation with any hurdles. Around the world all nations sequentially identifying the method to reduce the power loss in the transmission and subsequently it improve the quality of power. MFO algorithm has been formed based on the innate events of Melon fly. Due their very excellent eyesight and mutual supportive behaviour Melon fly will find the food without difficulty. By smell and vision the Melon fly will move to the best location form the current location. In the preliminary level Melon flies will search the food in multiple directions and they may be far away from the food source, it like scattering in the plane. Then Spontaneous Process Algorithm (SPA) is designed to solve the optimal reactive power problem Formulation of the projected algorithm is done by imitating the process done during nuclear fission and fusion. Every item of a nucleus attribute symbolizes each solution variable. Sequence of operators directs the nucleus and in order to avoid the local optimum it will imitate the dissimilar condition of reaction. In the exploration space nucleus symbolizes the variables and potential solution. Levy flight has been intermingled in the procedure to enhance the diversification and intensification in the search. Evaluation of validity of the Melon Fly Optimization (MFO) Algorithm and Spontaneous Process Algorithm (SPA) is done in IEEE 30-bus system by considering voltage stability (L-index) and also devoid of L-index criterion. Minimization of voltage deviation, voltage stability enhancement and power loss minimization has been achieved.

A Novel Deep Learning-based Whale Optimization Algorithm for Prediction of Breast Cancer

HIGHLIGHTS Novel whale optimization algorithm is proposed for prediction of breast cancer. Deep learning-based WOA adjusts the CNN structure as per maximum detection accuracy. Proposed method achieves 92.4% accuracy in comparison to 90.3%. Validity of method is evaluated with magnifying factors like 40x, 100 x, 200x, 400x.

Abstract Breast cancer is one of the most common cancers among women that cause billions of deaths worldwide. Identification of breast cancer often depends on the examination of digital biomedical photography such as the histopathological images of various health professionals, and clinicians. Analyzing histopathological images is a unique task and always requires special knowledge to conclude investigating these types of images. In this paper, a novel efficient technique has been proposed for the detection and prediction of breast cancer at its early stage. Initially, the dataset of images is used to carry out the pre-processing phase, which helps to transform a human pictorial image into a computer photographic image and adjust the parameters appropriate to the Convolutional neural network (CNN) classifier. Afterward, all the transformed images are assigned to the CNN classifier for the training process. CNN classifies incoming breast cancer clinical images as malignant and benign without prior information about the occurrence of cancer. For parameter optimization of CNN, a deep learning-based whale optimization algorithm (WOA) has been proposed which proficiently and automatically adjusts the CNN network structure by maximizing the detection accuracy. We have also compared the obtained accuracy of the proposed algorithm with a standard CNN and other existing classifiers and it is found that the proposed algorithm supersedes the other existing algorithms.

Stress analysis of the molar with the all-ceramic crown prosthesis based on centric occlusal optimization / 生物医学工程学杂志

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.

A novel pectoral muscle segmentation from scanned mammograms using EMO algorithm

Mammogram images are majorly used for detecting the breast cancer. The level of positivity of breast cancer is detected after excluding the pectoral muscle from mammogram images. Hence, it is very significant to identify and segment the pectoral muscle from the mammographic images. In this work, a new multilevel thresholding, on the basis of electro-magnetism optimization (EMO) technique, is proposed. The EMO works on the principle of attractive and repulsive forces among the charges to develop the members of a population. Here, both Kapur's and Otsu based cost functions are employed with EMO separately. These standard functions are executed over the EMO operator till the best solution is achieved. Thus, optimal threshold levels can be identified for the considered mammographic image. The proposed methodology is applied on all the three twenty-two mammogram images available in mammographic image analysis society dataset, and successful segmentation of the pectoral muscle is achieved for majority of the mammogram images. Hence, the proposed algorithm is found to be robust for variations in the pectoral muscle.

Spatial epidemiological characteristics and prediction models of bacterial dysentery in Chongqing from 2009 to 2016 based on meteorological elements / 上海交通大学学报（医学版）

Objective: To analyze the spatial epidemiological characteristics of bacillary dysentery and its correlation with meteorological elements in Chongqing, and to construct its incidence prediction model, thus providing scientific basis for the prevention and control of bacterial dysentery. Methods: The data of bacterial dysentery cases and meteorological factors from 2009 to 2016 in Chongqing was collected in this study. Descriptive methods were employed to investigate the epidemiological distribution of bacillary dysentery. Spatiotemporal scanning statistics was used to analyze spatiotemporal characteristics of bacillary dysentery. DCCA coefficient method was used to quantify the correlation between the incidence of bacillary dysentery and meteorological elements. Both Boruta algorithm and particle swarm optimization algorithm (PSO) combined with support vector machine for regression model (SVR) were used to establish the prediction model for the incidence of bacterial dysentery. Results: ①The mean annual reported incidence of bacillary dysentery in Chongqing from 2009 to 2016 was 29.394/100 000. Children <5 years old had the highest incidence (295.892/100 000) among all age categories and scattered children had the highest proportion (50.335%) among all occupation categories. The seasonal incidence peak was from May to October. Bacterial dysentery showed a significant spatial-temporal aggregation that the most likely clusters for disease was found mainly in the main urban areas and main gathering time was from June to October. ②The most important meteorological elements associated with the incidence of bacterial dysentery were monthly mean atmospheric pressure (ρDCCA=-0.918), monthly mean maximum temperature (ρDCCA=0.875) and monthly mean temperature (ρDCCA=0.870). ③The mean squared error (MSE), mean absolute percentage error (MAPE) and square correlation coefficient (R2) of PSO_SVR model constructed based on meteorological elements were 0.055, 0.101 and 0.909, respectively. Conclusion: The main urban areas of Chongqing and the northeast of Chongqing should be regarded as the key areas for the prevention and control of bacillary dysentery. At the same time, according to the characteristics of bacillary dysentery, relevant health departments should take targeted measures to control the spread and prevalence of bacillary dysentery among children <5 years old, scattered children and farmers. The PSO_SVR model constructed based on meteorological elements has good predictive performance and can provide scientific theoretical support for the prevention and control of bacterial dysentery.

Comparison of IPSA and HIPO inverse planning optimization algorithms for cervical cancer intracavitary/interstitial brachytherapy / 中华放射医学与防护杂志

Objective To compare the difference of dose distribution between inverse planning simulated annealing (IPSA) and hybrid inverse treatment planning and optimization (HIPO) in 3D brachytherapy plan of cervical cancer,and to provide evidence for selection of reverse planning optimization method for cervical cancer brachytherapy.Methods From Dec 2016 to May 2017,totally 43 cases of patients with cervical cancer radical surgery were selected.Original IPSA brachytherapy treatment plan optimization was applied to all cases.Based on the information of original image,IPSA and HIPO plans were established according to the same initial conditions.Parameters of Dg0,D100,V100％,Homogeneity Index (HI),and conformal index (CI) of the bladder,rectum and sigmoid D2 cm3 data for High-Risk Clinical Target Volume (HR-CTV) were assessed.Results There was no statistically significant difference in D90,D100 and CI for HR-CTV between the two groups.But the V100％ of HR-CTV in HIPO group was significantly higher than that in IPSA group [(87.72 ±0.49)％ vs.(85.01 ± 0.55)％,t =2.54,P ＜0.05].Furthermore,HI in HIPO group was (0.51 ±0.08),which was higher than that in IPSA group (0.42 ± 0.06),and the difference was statistically significant (t =3.02,P ＜ 0.05).Compared with IPSA,bladder D2 cm3 and rectum D2 cm3 [(3.04 ± 0.37) Gy] for HIPO plan were lower [(3.42 ± 0.17) Gy vs.(3.57 ± 0.28) Gy,(3.04 ± 0.37) Gy vs.(3.57 ± 0.28) Gy],which had reached statistical significance (t =0.27,0.19,P ＜ 0.05).There was no statistical significance in the D2 cm3 dose of sigmoid.Conclusions In the treatment of cervical cancer,better target area HI and less irradiated dose of bladder and rectum can be obtained by HIPO optimization than IPSA optimization.

Optimization of beam orientations in three-dimensional conformal radiotherapy with the genetic algorithm / 中华放射肿瘤学杂志

Objective To develop a beam orientation optimization algorithm for the gantry orientation in three-dimensional conformal radiotherapy(3 DCRT).Methods Patients' data were imported from the Pinnacle v 7.2 treatment planning system.including the DICOMRT and dose distribution files.These imported files were merged using a uniforiB coordinate system.The algorithm determined the optimized beam weight for each beam group and optimized the beam orientation with genetic algorithm.The optimized parameters,including the optimized beam orientations and weights,were exposed back to the Pinnacle v 7.2 to compare with the conventional 3DCRT plan.The optimized algorithm was implemented with our in-house program. The dose distributions, the DVH diagram and the conformity index of two lung cancer patients were compared. Results for the two lung cancer patients,the conformity index of the optimized plan(0.59 and 0.7)was higher than the conwentional 3DCRT plan(0.36 and 0.58).The maximum dose in spinal cord was reduced by 17.8%and 22.4%,the lung V20 reduced by 3.12%and 4.35%,and V30 reduced by 4.47%and 1.49%.For the brain tumor patient. the dose of lens and eyes was also decreased significantly. Conclusion This beam orientation optimization can be used as an assistant planning tool.

Immune clonal selection optimization method with combining mutation strategies / 药物分析学报

In artificial immune optimization algorithm, the mutation of immune cells has been considered as the key operator that determines the algorithm performance. Traditional immune optimization algorithms have used a single mutation operator, typically a Gaussian. Using a variety of mutation operators that can be combined during evolution to generate different probability density function could hold the potential for producing better solutions with less computational effort. In view of this, a linear combination mutation operator of Gaussian and Cauchy mutation is presented in this paper, and a novel clonal selection optimization method based on clonal selection principle is proposed also. The simulation results show the combining mutation strategy can obtain the same performance as the best of pure strategies or even better in some cases.

Immune clonal selection optimization method with combining mutation strategies / 西安交通大学学报·英文版

In artificial immune optimization algorithm, the mutation of immune cells has been considered as the key operator that determines the algorithm performance. Traditional immune optimization algorithms have used a single mutation operator, typically a Gaussian. Using a variety of mutation operators that can be combined during evolution to generate different probability density function could hold the potential for producing better solutions with less computational effort. In view of this, a linear combination mutation operator of Gaussian and Cauchy mutation is presented in this paper, and a novel clonal selection optimization method based on clonal selection principle is proposed also. The simulation results show the combining mutation strategy can obtain the same performance as the best of pure strategies or even better in some cases.