scholarly journals Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 5046 ◽  
Author(s):  
Lvwen Huang ◽  
Han Guo ◽  
Qinqin Rao ◽  
Zixia Hou ◽  
Shuqin Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Three Dimensional ◽  
Automatic Measurement ◽  
The Body ◽  
Surface Shape ◽  
Body Dimension ◽  
Qinchuan Cattle ◽  
Body Dimensions ◽  
Deep Model

For the time-consuming and stressful body measuring task of Qinchuan cattle and farmers, the demand for the automatic measurement of body dimensions has become more and more urgent. It is necessary to explore automatic measurements with deep learning to improve breeding efficiency and promote the development of industry. In this paper, a novel approach to measuring the body dimensions of live Qinchuan cattle with on transfer learning is proposed. Deep learning of the Kd-network was trained with classical three-dimensional (3D) point cloud datasets (PCD) of the ShapeNet datasets. After a series of processes of PCD sensed by the light detection and ranging (LiDAR) sensor, the cattle silhouettes could be extracted, which after augmentation could be applied as an input layer to the Kd-network. With the output of a convolutional layer of the trained deep model, the output layer of the deep model could be applied to pre-train the full connection network. The TrAdaBoost algorithm was employed to transfer the pre-trained convolutional layer and full connection of the deep model. To classify and recognize the PCD of the cattle silhouette, the average accuracy rate after training with transfer learning could reach up to 93.6%. On the basis of silhouette extraction, the candidate region of the feature surface shape could be extracted with mean curvature and Gaussian curvature. After the computation of the FPFH (fast point feature histogram) of the surface shape, the center of the feature surface could be recognized and the body dimensions of the cattle could finally be calculated. The experimental results showed that the comprehensive error of body dimensions was close to 2%, which could provide a feasible approach to the non-contact observations of the bodies of large physique livestock without any human intervention.

scholarly journals Non-Contact Body Measurement for Qinchuan Cattle with LiDAR Sensor

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3014 ◽  
Author(s):  
Lvwen Huang ◽  
Shuqin Li ◽  
Anqi Zhu ◽  
Xinyun Fan ◽  
Chenyang Zhang ◽  
...  
Keyword(s):  
Stress Responses ◽  
Three Dimensional ◽  
The Body ◽  
Data Series ◽  
Reconstruction Method ◽  
Body Measurement ◽  
Body Dimension ◽  
Qinchuan Cattle ◽  
Dimension Measurement ◽  
Voxel Grid

The body dimension measurement of large animals plays a significant role in quality improvement and genetic breeding, and the non-contact measurements by computer vision-based remote sensing could represent great progress in the case of dangerous stress responses and time-costing manual measurements. This paper presents a novel approach for three-dimensional digital modeling of live adult Qinchuan cattle for body size measurement. On the basis of capturing the original point data series of live cattle by a Light Detection and Ranging (LiDAR) sensor, the conditional, statistical outliers and voxel grid filtering methods are fused to cancel the background and outliers. After the segmentation of K-means clustering extraction and the RANdom SAmple Consensus (RANSAC) algorithm, the Fast Point Feature Histogram (FPFH) is put forward to get the cattle data automatically. The cattle surface is reconstructed to get the 3D cattle model using fast Iterative Closest Point (ICP) matching with Bi-directional Random K-D Trees and a Greedy Projection Triangulation (GPT) reconstruction method by which the feature points of cattle silhouettes could be clicked and calculated. Finally, the five body parameters (withers height, chest depth, back height, body length, and waist height) are measured in the field and verified within an accuracy of 2 mm and an error close to 2%. The experimental results show that this approach could be considered as a new feasible method towards the non-contact body measurement for large physique livestock.

scholarly journals Sequential Network with Residual Neural Network for Rotatory Machine Remaining Useful Life Prediction Using Deep Transfer Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Hao Zhang ◽  
Qiang Zhang ◽  
Siyu Shao ◽  
Tianlin Niu ◽  
Xinyu Yang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Life Prediction ◽  
Feature Learning ◽  
High Accuracy ◽  
Remaining Useful Life ◽  
Learning Ability ◽  
Model Parameters ◽  
Deep Model ◽  
Useful Life

Deep learning has a strong feature learning ability, which has proved its effectiveness in fault prediction and remaining useful life prediction of rotatory machine. However, training a deep network from scratch requires a large amount of training data and is time-consuming. In the practical model training process, it is difficult for the deep model to converge when the parameter initialization is inappropriate, which results in poor prediction performance. In this paper, a novel deep learning framework is proposed to predict the remaining useful life of rotatory machine with high accuracy. Firstly, model parameters and feature learning ability of the pretrained model are transferred to the new network by means of transfer learning to achieve reasonable initialization. Then, the specific sensor signals are converted to RGB image as the specific task data to fine-tune the parameters of the high-level network structure. The features extracted from the pretrained network are the input into the Bidirectional Long Short-Term Memory to obtain the RUL prediction results. The ability of LSTM to model sequence signals and the dynamic learning ability of bidirectional propagation to time information contribute to accurate RUL prediction. Finally, the deep model proposed in this paper is tested on the sensor signal dataset of bearing and gearbox. The high accuracy prediction results show the superiority of the transfer learning-based sequential network in RUL prediction.

scholarly journals How predation shaped fish: the impact of fin spines on body form evolution across teleosts

2015 ◽  
Vol 282 (1819) ◽  
pp. 20151428 ◽  
Author(s):  
S. A. Price ◽  
S. T. Friedman ◽  
P. C. Wainwright
Keyword(s):  
Evolutionary Dynamics ◽  
Morphological Changes ◽  
Evolutionary Relationship ◽  
Vertical Plane ◽  
The Body ◽  
Body Dimension ◽  
Body Depth ◽  
Body Dimensions ◽  
The Impact ◽  
Fin Spines

It is well known that predators can induce morphological changes in some fish: individuals exposed to predation cues increase body depth and the length of spines. We hypothesize that these structures may evolve synergistically, as together, these traits will further enlarge the body dimensions of the fish that gape-limited predators must overcome. We therefore expect that the orientation of the spines will predict which body dimension increases in the presence of predators. Using phylogenetic comparative methods, we tested this prediction on the macroevolutionary scale across 347 teleost families, which display considerable variation in fin spines, body depth and width. Consistent with our predictions, we demonstrate that fin spines on the vertical plane (dorsal and anal fins) are associated with a deeper-bodied optimum. Lineages with spines on the horizontal plane (pectoral fins) are associated with a wider-bodied optimum. Optimal body dimensions across lineages without spines paralleling the body dimension match the allometric expectation. Additionally, lineages with longer spines have deeper and wider body dimensions. This evolutionary relationship between fin spines and body dimensions across teleosts reveals functional synergy between these two traits and a potential macroevolutionary signature of predation on the evolutionary dynamics of body shape.

scholarly journals Three-dimensional visualization and a deep-learning model reveal complex fungal parasite networks in behaviorally manipulated ants

2017 ◽  
Vol 114 (47) ◽  
pp. 12590-12595 ◽  
Author(s):  
Maridel A. Fredericksen ◽  
Yizhe Zhang ◽  
Missy L. Hazen ◽  
Raquel G. Loreto ◽  
Colleen A. Mangold ◽  
...  
Keyword(s):  
Deep Learning ◽  
Behavioral Control ◽  
Three Dimensional ◽  
The Body ◽  
Fungal Parasite ◽  
Carpenter Ant ◽  
Block Face ◽  
Species Specific ◽  
Deep Learning Model ◽  
Ophiocordyceps Unilateralis

Some microbes possess the ability to adaptively manipulate host behavior. To better understand how such microbial parasites control animal behavior, we examine the cell-level interactions between the species-specific fungal parasite Ophiocordyceps unilateralis sensu lato and its carpenter ant host (Camponotus castaneus) at a crucial moment in the parasite’s lifecycle: when the manipulated host fixes itself permanently to a substrate by its mandibles. The fungus is known to secrete tissue-specific metabolites and cause changes in host gene expression as well as atrophy in the mandible muscles of its ant host, but it is unknown how the fungus coordinates these effects to manipulate its host’s behavior. In this study, we combine techniques in serial block-face scanning-electron microscopy and deep-learning–based image segmentation algorithms to visualize the distribution, abundance, and interactions of this fungus inside the body of its manipulated host. Fungal cells were found throughout the host body but not in the brain, implying that behavioral control of the animal body by this microbe occurs peripherally. Additionally, fungal cells invaded host muscle fibers and joined together to form networks that encircled the muscles. These networks may represent a collective foraging behavior of this parasite, which may in turn facilitate host manipulation.

Application of the Three Dimensional Coordinate Measuring Machine (CAD/CAM for the New Cosmetic Hand)

1989 ◽  
Vol 1 (3) ◽  
pp. 192-201
Author(s):  
Yukio Saito ◽  
◽  
Takanori Higashihara ◽  
Torn Oshima ◽  
Takamitu Tajima ◽  
...  
Keyword(s):  
Three Dimensional ◽  
Coordinate Measuring Machine ◽  
Automatic Measurement ◽  
Surface Shape ◽  
Human Hand ◽  
Shape Processing ◽  
Soft Objects ◽  
Cad Cam ◽  
Measuring Machine ◽  
Three Dimensional Coordinate

The purpose of this research was to develop a CAD/ CAM system for soft objects such as the human hand. In this article are described the various steps in this process, including digitization of the shape by automatic measurement of the object shape processing such as shape interpolation and correction, additional shape processing, motion simulation for the digitized soft model, and reproduction of the shape as a positive model. As an example, we established a method for making a new cosmetic hand that could meet the necessary requirements of shape and functionality. For the shape, we measured the natural hand of a disabled person automatically with a three-dimensional coordinate measuring machine, performed data processing, and produced a positive model for the cosmetic hand. For functionality, we simulated the change of surface shape caused by finger motion using the shape of the measured hand, and then developed the inside mechanism of the cosmetic hand. This article describes the system developed for application to the cosmetic hand.

The Diagnosis Of Diabetic Retinopathy By Means Of Transfer Learning And Fine-Tuned Dense Layer Pipeline

Mekatronika ◽  
2020 ◽  
Vol 2 (1) ◽  
pp. 68-72
Author(s):  
Abdulaziz Abdo Salman ◽  
Ismail Mohd Khairuddin ◽  
Anwar P.P. Abdul Majeed ◽  
Mohd Azraai Mohd Razman
Keyword(s):  
Blood Flow ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Blood Vessels ◽  
Transfer Learning ◽  
The Body ◽  
Dense Layer ◽  
Fundus Images ◽  
Detection Approach ◽  
Deep Learning Model

Diabetes is a global disease that occurs when the body is disabled pancreas to secrete insulin to convert the sugar to power in the blood. As a result, some tiny blood vessels on the part of the body, such as the eyes, are affected by high sugar and cause blocking blood flow in the vessels, which is called diabetic retinopathy.  This disease may lead to permanent blindness due to the growth of new vessels in the back of the retina causing it to detach from the eyes. In 2016, 387 million people were diagnosed with Diabetic retinopathy, and the number is growing yearly, and the old detection approach becomes worse. Therefore, the purpose of this paper is to computerize the old method of detecting different classes of DR from 0-4 according to severity by given fundus images. The method is to construct a fine-tuned deep learning model based on transfer learning with dense layers. The used models here are InceptionV3, VGG16, and ResNet50 with a sharpening filter. Subsequently, InceptionV3 has achieved 94% as the highest accuracy among other models.  

Influence of Trapped Air on the Slamming of a Ship

2003 ◽  
Vol 47 (03) ◽  
pp. 187-193 ◽  
Author(s):  
Ken Takagi ◽  
Junya Dobashi
Keyword(s):  
Local Structure ◽  
Surface Deformation ◽  
Three Dimensional ◽  
The Body ◽  
Surface Shape ◽  
Natural Period ◽  
Trapped Air ◽  
Calm Water ◽  
Spring System ◽  
The Impact

We describe a theoretical approach to a distorted plate penetrating calm water surface as a flow model of the water impact in rough seas. Further simplifications are employed so that the structure of ship is modeled by a tandem mass and spring system and a sequence of circular hollows is used as a bottom shape of the body instead of the surface shape of short crested waves. The results show that the model-scale ship experiences much larger stress at the local structure because of the influence of trapped air. Some results for the full-scale ship show that the three-dimensional effect, that is, the shape of sea surface deformation, is dominant for the cushioning of the impact force, and the trapped air affects some of this effect according to the magnitude of P and the natural period of the local structure.

Biometric measurement of static space required by weaned piglets kept in groups of eight during 6 weeks

2019 ◽  
Vol 59 (7) ◽  
pp. 1327 ◽  
Author(s):  
M. Fels ◽  
K. Konen ◽  
E. Hessel ◽  
N. Kemper
Keyword(s):  
Three Dimensional ◽  
Automatic Measurement ◽  
The Body ◽  
Biometric Data ◽  
Total Period ◽  
Nursery Pigs ◽  
Floor Area ◽  
Space Allocation ◽  
Space Requirements ◽  
Static Space

Adequate space allocation is deemed to be an important criterion for animal welfare in modern pig farming. However, it is not a simple matter to determine how much space a group of pigs needs, and precise, animal-based data about the floor area needed by the body dimensions of group-housed pigs in different weight categories are currently lacking. So as to collect biometric data on the static space of weaned pigs kept in groups and to evaluate current spatial requirements, an automatic measurement of the floor area covered by the pigs’ bodies within groups was performed. Consequently, the resulting free space in a pen, available for (non-) locomotor behaviours, was calculated. In three batches, two groups of eight piglets each were formed after weaning. Using three-dimensional cameras that recorded a piglets’ pen from top view and a software for image analysis, the exact static space of a group considering different body positions was measured and specified in square centimetres. Measurements were taken weekly for a total period of 6 weeks per batch. The area covered by the bodies of a group of eight piglets increased almost linearly with increasing average bodyweight (R 2 = 0.99, n = 1645 images). The highest mean static space was measured in Week 6 (1.54 m2, average bodyweight: 25.2 kg) when 100% of piglets were lying with less than 50% huddling. When 100% of piglets within a group were lying, more than 50% huddling reduced the mean static space to 1.4 m2 (P < 0.05). When all pigs of a group were lying, significantly more space was covered than in situations when all pigs of a group were standing (1.54 m2 vs 1.36 m2, P < 0.05). Exclusively in Week 1, when piglets were lying with more than 50% huddling, the space covered by the group was slightly reduced compared with the situation when 100% of piglets were standing. By the automatic method, realistic results on the static space of piglets kept in groups were achieved. Space requirements of the largest animals in the most space-demanding body positions should be the basis for space recommendations for nursery pigs.

Investigation of chest girth and height variation affecting other body dimensions for men’s upper body clothes pattern grading

2019 ◽  
Vol 31 (3) ◽  
pp. 415-430 ◽  
Author(s):  
Hyunsook Han
Keyword(s):  
The Body ◽  
Upper Body ◽  
Variation Analysis ◽  
Body Dimension ◽  
Data Set ◽  
Body Dimensions ◽  
Content Type ◽  
Pattern Grading ◽  
Size Groups ◽  
Chest Girth

Purpose The purpose of this paper is to investigate the chest girth and height related to men’s upper body dimensions to develop men’s grading system for semi-customized clothing. Design/methodology/approach A data set of the 3,012 men between the age group of 18 and 59 years from 6th Size Korea was used in this study. The men’s upper body dimensions were tested in terms of five horizontal lengths, seven circumferences and seven vertical lengths. Experiment and data analysis were carried out with two methods: one is multiple linear regression with chest girth and height as each independent variable and the other is calculating variation among chest girth size groups and height size groups, respectively. Findings Regression analysis showed that some horizontal lengths are affected not only by chest girth, but also by height, and some vertical lengths are affected not only by height, but also by chest girth. In variation analysis it was found that the variation value for each part of the body is different and it was observed that with an increase in chest girth vertical length also increases. In variation analysis of height, it is found that some horizontal body dimensions and hip girth increase with an increase in height. In the comparison of upper body dimension variation among height groups with the size based on the chest girth, we found that a tall person who already has long vertical length is less affected by the increase in dimensions by increases in their horizontal girth than a short person. Originality/value The findings showed detailed numerical body shape changes according to chest girth and height, and it may be used as the basis for determining pattern grading values by chest girth or height.

scholarly journals Automatic Measurement of Inner Ear in Different Mammals1

2020 ◽  
Author(s):  
Yi Du ◽  
Han-dai Qin ◽  
Chen Liu ◽  
Da Liu ◽  
Shuo-long Yuan ◽  
...  
Keyword(s):  
Inner Ear ◽  
Semicircular Canal ◽  
Three Dimensional ◽  
Semicircular Canals ◽  
Automatic Measurement ◽  
The Body ◽  
Human Data ◽  
Dimensional Models ◽  
Three Dimensional Models ◽  
Mini Pigs

AbstractObjectiveThe aim of this research is to develop an accurate and automatic measuring method based on the aid of centerline to construct three dimensional models of inner ear in different mammals and to assess the morphological variations.MethodsThree adult healthy mice, three adult guinea pigs, three adult mini pigs and one left temporal bone of human were included in this research. All 18 animal specimens and the human sample were scanned with the use of Micro-CT. After being segmented, three-dimensional models of the inner ear in different mammals were reconstructed using Mimics. A novel method with the use of centerline was established to estimate the properties of 3D models and to calculate the length, volume and angle parameters automatically.ResultsMorphological models of inner ears in different mammals have been built, which describe detailed shape of cochlear, vestibule, semicircular canals and common crus. Mean value of lengths and volumes of the cochlear, lateral semicircular canal, superior semicircular canal and posterior semicircular canal, tended to increase with the body size of the mammals, showed the proximity to the human data in mini pig. The angles between the semicircular canal planes showed differences between mammals. The mean values of semicircular canals of mice and mini pigs closely resembled to human data in numerical assessment.ConclusionThe automatic measurement of the inner ear based on centerline builds an effective way to assess lengths, volumes and angles of three-dimensional structures. This study provides a theoretical basis for mechanical analysis of inner ear in different mammals and proves the similarity between mini pig and human.

Sign in / Sign up

Export Citation Format

Share Document