the proceedings contain 77 papers. the topics discussed include: 5.8 GHz ISM band Yagi-Uda antenna implementation using genetic algorithms;a neural-network based algorithm oriented to identifying the damage degree cau...
ISBN:
(纸本)9781728147468
the proceedings contain 77 papers. the topics discussed include: 5.8 GHz ISM band Yagi-Uda antenna implementation using genetic algorithms;a neural-network based algorithm oriented to identifying the damage degree caused by the meloidogyne incognita nematode in digital images of vegetable roots;design and simulation of strain gauge of 3 meanders, for the reduction of external factors;a microencapsulation process of bacterial spores to obtain a biomaterial of sustainable construction;early detection of saline soils by using satellite images in the Peruvian province of huaura;bibliometric and impact analysis of the project management offices in Colombia;and monitoring automation process to improve the evaluation of competency learning for higher education.
this paper aims to investigate the capability of mixed-integer linear programming (MILP) method and genetic algorithm (GA) to solve binary problem (BP). A comparative study on the MILP method and GA with default and t...
详细信息
ISBN:
(纸本)9781538657485
this paper aims to investigate the capability of mixed-integer linear programming (MILP) method and genetic algorithm (GA) to solve binary problem (BP). A comparative study on the MILP method and GA with default and tuned setting to find out an optimal solution is presented. the mixed-integer programming library (MIPLIB 2010) is used to test and evaluate algorithms. the evaluation is shown in quality of the solution and the execution time of computation. the results show that GA is superior to MILP in execution time with inconsistent results. However, MILP is superior to GA in quality of the solution with more stable results.
the proceedings contain 14 papers. the special focus in this conference is on Computational Methods and Clinical Applications for Spine Imaging. the topics include: Deep learning framework for fully automated interver...
ISBN:
(纸本)9783030137359
the proceedings contain 14 papers. the special focus in this conference is on Computational Methods and Clinical Applications for Spine Imaging. the topics include: Deep learning framework for fully automated intervertebral disc localization and segmentation from multi-modality MR images;IVD-net: Intervertebral disc localization and segmentation in MRI with a multi-modal UNet;Intervertebral disc segmentation and localization from multi-modality MR images with 2.5D multi-scale fully convolutional network and geometric constraint post-processing;Automatic segmentation of lumbar spine MRI using ensemble of 2D algorithms;Evaluation and comparison of automatic intervertebral disc localization and segmentation methods with 3D multi-modality MR images: A grand challenge;Predicting scoliosis in DXA scans using intermediate representations;Fast registration of CT with intra-operative ultrasound images for spine surgery;Automated grading of modic changes using CNNs – Improving the performance with mixup;error estimation for appearance model segmentation of musculoskeletal structures using multiple, independent sub-models;automated segmentation of intervertebral disc using fully dilated separable deep neural networks;Intensity standardization of skeleton in follow-up whole-body MRI;towards a deformable multi-surface approach to ligamentous spine models for predictive simulation-based scoliosis surgery planning.
Detection of surgical instrument has been implemented in minimally invasive computer assisted surgery domain but detection of desired parts of surgical instrument has not been implemented properly. Previous researches...
详细信息
ISBN:
(数字)9781728194370
ISBN:
(纸本)9781728194387
Detection of surgical instrument has been implemented in minimally invasive computer assisted surgery domain but detection of desired parts of surgical instrument has not been implemented properly. Previous researches have divided surgical instrument into two parts: End-effector and Shaft [12], which are not adequate to detect the components clearly. In this paper, we propose solution to improve accuracy and processing time of instrument detection. the novel detection has been implemented using deep learning algorithms-Convolutional Neural Network (CNN). the CNN uses kernel to perform feature extraction. the feature extraction includes convolution, batch normalisation, ReLu, max pooling and drop. In addition, selective kernel has been used during convolution to detect the parts of surgical instrument. there are four different types of datasets have been used for the execution. the proposed solution has giving promised results as there are nearly 2% improvement in accuracy and nearly 2s drop-in processing time. ReLu activation in convolution network and 20% dropout from output of convolution, not only reduces the processing time but also improved accuracy of detection.
there is still a big gap between China and other advanced shipbuilding countries, such as digital fields, networking and intellectualization. the inventory management leads to more inventories, growing cost, slower co...
详细信息
From 1997 to 2006, China's railway has undergone six large-scale speed-raising reconstruction, and some of the speed has reached 250KM/h. Withthe development of train speed, the pantograph-cantenary system become...
详细信息
ISBN:
(数字)9781728161365
ISBN:
(纸本)9781728161372
From 1997 to 2006, China's railway has undergone six large-scale speed-raising reconstruction, and some of the speed has reached 250KM/h. Withthe development of train speed, the pantograph-cantenary system becomes more and more important. Since infrared image has light penetration, this paper fuses infrared and visible images to get more information about the pantograph-cantenary so that train drivers can learn more about the pantograph-cantenary situation. Existing fusion methods typically use the same representations and extract the similar characteristics for different source images. However, it may don't work for infrared and visible images. In this paper, we use the fusion algorithm named Gradient Transfer Fusion (GTF), which can keep the thermal radiation and appearance information simultaneously. To prove the effectiveness of the GTF method, it is compared with other 17 fusion algorithms from quantitative aspects. Furthermore, the parameter in the GTF method is analyzed and selected for better fusion results. Finally, color image fusion which is an improvement to the GTF method preserving the color information of the visible image in the fused image is proposed and it is tested on publicly available data sets to prove its availability.
Vertex cover (VC) is one of the most fundamental graph-theoretical problems and has been widely used in wireless sensor networks (WSNs), particularly for the link monitoring problem. It is well known that a solution t...
详细信息
ISBN:
(纸本)9781538663929
Vertex cover (VC) is one of the most fundamental graph-theoretical problems and has been widely used in wireless sensor networks (WSNs), particularly for the link monitoring problem. It is well known that a solution to the independent set problem (IS), which is another fundamental graph-theoretical problem, is complement of a VC. Self-stabilization is an important concept for designing fault tolerance systems. there have been many self-stabilizing VC and IS algorithms in the field. Even though a self-stabilizing IS algorithm can provide VC solutions, it does not give a theoretical guarantee on approximation ratio. In this work, we focus on practical fault tolerance performance of self-stabilizing IS algorithms in case of a vertex cover problem, particularly link monitoring in WSNs. We implement all existing self-stabilizing VC and IS algorithms and make simulations assuming a WSN in which nodes run synchronously. Results show that self-stabilizing IS algorithms in general are able to find better covers than VC algorithms, as they provide roughly 15% smaller solution sets. Furthermore, IS algorithmsthat run under distributed scheduler converges to a desired configuration in considerably less number of rounds than VC algorithms.
Evolutionary optimizers, such as genetic algorithms, have earlier been successfully applied to find the parameter values for the fuel cell polarization curve models. the structure of these, typically semi-empirical, m...
详细信息
ISBN:
(纸本)9781538650653
Evolutionary optimizers, such as genetic algorithms, have earlier been successfully applied to find the parameter values for the fuel cell polarization curve models. the structure of these, typically semi-empirical, models have evolved during the decades. In this study, the model structures were reviewed and a new model structure was generated. Genetic algorithms were used to determine the optimized model structure with linear model parameters. Four different fuel cells, one with varying operating conditions, were studied. the results show that the model can outperform the semi-empirical model utilized in number of studies without increasing the model complexity.
the seriation problem is an important problem in combinatorial optimization. the goal of seriation is to find a linear order for data objects to reveal structural information given a loss or a merit objective function...
详细信息
ISBN:
(纸本)9781538657485
the seriation problem is an important problem in combinatorial optimization. the goal of seriation is to find a linear order for data objects to reveal structural information given a loss or a merit objective function as an objective function. For the seriation problem, finding an optimal solution using exact algorithms (e.g., branch-and-bound) to find the optimal solution is currently impractical for problems with more than 35 objects. In this paper, we develop a new heuristic procedure to maximize the gradient measure which is our selected merit objective function. the proposed heuristic incorporates search intensification and diversification into standard tabu search (TS) algorithm. From our experimental results, it shows that intensification and diversification tabu search (IDTS) outperforms the standard TS algorithms in terms of efficiency, effectiveness, and robustness.
this study evaluated the usability of the children's Urdu learning mobile Apps for Tablet-PCs. the pre-test questionnaire based on demographic information of the participants, post-test questionnaire using the fun...
详细信息
ISBN:
(纸本)9783319917436;9783319917429
this study evaluated the usability of the children's Urdu learning mobile Apps for Tablet-PCs. the pre-test questionnaire based on demographic information of the participants, post-test questionnaire using the fun Toolkit and the usability tasks were developed for collecting data from the children. the usability test was conducted by 232 participating children having age between 5 and 10 years of the primary schools. After filling the demographic questionnaire, the usability tasks were given to the children where time was recorded for each of the tasks. Afterwards, the post-test questionnaire was administered among the children in order to gather their opinion about the apps. the study result illustrated that the App3 was the best App in terms of efficiency and effectiveness. According to the Smileyometer results, the children reported more fun in using the App3. the Again-Again table results also show that the children wanted to use the App3 again and again. this study proposed the best Urdu learning mobile App from learning perspective for the children which is recommended to be complemented withthe existing traditional classroom learning in the schools of the country for enhancing their learning outcomes.
暂无评论