Random Forest Algorithm with a Half-Voting and Weighted Decision Trees for Interior Pedestrian Tracking

The traditional Zero Velocity Updating Algorithm is being used to correct the accumulated errors of the device effectively. However, as the threshold value of the traditional Zero Velocity Updating algorithm is fixed, it is only suitable for a single motion mode. When indoor pedestrian motion includes multiple motion modes, the positioning accuracy will be greatly reduced. In this paper, we propose an adaptive Zero Velocity Updating method for multi-motion mode using half- voting Random Forest. We analysed the selection of Zero Velocity Updating threshold value for stilling, walking, running, going upstairs and downstairs for the interior pedestrian. Then we recognize pedestrian motion by Random Forest with a Half-Voting and Weighted Decision Trees. Finally according to the result of recognition adjust the threshold adaptively to determine the zero velocity intervals accurately. In order to verify the feasibility and effectiveness of the method proposed in this paper, field experiments were carried out with the inertial navigation module developed by our laboratory. The experimental results show that when indoor pedestrians perform multi-mode motion, the positioning error is 0.5m.

Download Full-text

A Novel Method for Constructing Multi-Mode Deployable Polyhedron Mechanisms Using Symmetric Spatial RRR Compositional Units

Volume 5A: 42nd Mechanisms and Robotics Conference ◽

10.1115/detc2018-85100 ◽

2018 ◽

Cited By ~ 1

Author(s):

Jieyu Wang ◽

Xianwen Kong

Keyword(s):

Kinematic Chain ◽

Degree Of Freedom ◽

Single Loop ◽

Kinematic Chains ◽

The Third ◽

Motion Modes ◽

3D Printed ◽

Novel Method ◽

Multi Mode ◽

Motion Mode

A novel construction method is proposed to construct multimode deployable polyhedron mechanisms (DPMs) using symmetric spatial RRR compositional units, a serial kinematic chain in which the axes of the first and the third revolute (R) joints are perpendicular to the axis of the second R joint. Single-loop deployable linkages are first constructed using RRR units and are further assembled into polyhedron mechanisms by connecting single-loop kinematic chains using RRR units. The proposed mechanisms are over-constrained and can be deployed through two approaches. The prism mechanism constructed using two Bricard linkages and six RRR limbs has one degree-of-freedom (DOF). When removing three of the RRR limbs, the mechanism obtains one additional 1-DOF motion mode. The DPMs based on 8R and 10R linkages also have multiple modes, and several mechanisms are variable-DOF mechanisms. The DPMs can switch among different motion modes through transition positions. Prototypes are 3D-printed to verify the feasibility of the mechanisms.

Download Full-text

Variable Degree-of-Freedom Spatial Mechanisms Composed of Four Circular Translation Joints

Volume 10: 44th Mechanisms and Robotics Conference (MR) ◽

10.1115/detc2020-22332 ◽

2020 ◽

Author(s):

Xianwen Kong

Keyword(s):

Configuration Space ◽

Screw Theory ◽

Degree Of Freedom ◽

Variable Degree ◽

Circular Trajectory ◽

Spatial Mechanism ◽

Spatial Mechanisms ◽

Motion Modes ◽

Multi Mode ◽

Motion Mode

Abstract This paper deals with the construction and reconfiguration analysis of a spatial mechanism composed of four circular translation (G) joints. Two links connected by a G joint, which can be in different forms such as a planar parallelogram, translate along a circular trajectory with respect to each other. A spatial 4G mechanism, which is composed of four G joints, usually has 1-DOF (degree-of-freedom). Firstly, a 2-DOF 4G mechanism is constructed. Then a novel variable-DOF spatial 4G mechanism is constructed starting from the 2-DOF 4G mechanism using the approach based on screw theory. Finally, the reconfiguration analysis is carried out in the configuration space using dual quaternions. The analysis shows that the variable-DOF spatial 4G mechanism has one 2-DOF motion mode and one to two 1-DOF motion modes and reveals how the 4G mechanism can switch among these motion modes. By removing one link from two adjacent G joints each and two links from each of the remaining two G joints, we can obtain a queer-rectangle and a queer-parallelogram, which are the generalization of the queer-square or derivative queer-square in the literature. The approach in this paper can be extended to the analysis of other types of coupled mechanisms using cables and gears and multi-mode spatial mechanisms involving G joints.

Download Full-text

A Single-Loop 7R Spatial Mechanism That Has Three Motion Modes With the Same Instantaneous DOF but Different Finite DOF

Volume 5B: 42nd Mechanisms and Robotics Conference ◽

10.1115/detc2018-85125 ◽

2018 ◽

Author(s):

Xianwen Kong ◽

Andreas Müller

Keyword(s):

Higher Order ◽

Mobility Analysis ◽

Single Loop ◽

Plane Symmetric ◽

Spatial Mechanism ◽

Motion Modes ◽

Regular Configuration ◽

Kinematic Loop ◽

Multi Mode ◽

Motion Mode

Multi-mode mechanisms, including kinematotropic mechanisms, are a class of reconfigurable mechanisms that can switch motion modes with the same or different DOF (degree-of-freedom). For most of the multi-mode mechanisms reported in the literature, the instantaneous (or differential) DOF and finite DOF in a motion mode are equal. In this paper, we will discuss the construction, reconfiguration analysis, and higher-order mobility analysis of a multi-mode single-loop 7R mechanism that has three motion modes with the same instantaneous DOF but different finite DOF. Firstly, the novel multi-mode single-loop 7R spatial mechanism is constructed by inserting one revolute (R) joint into a plane symmetric Bennett joint-based 6R mechanism for circular translation. The reconfiguration analysis is then carried out in the configuration space by solving a set of kinematic loop equations based on dual quaternions and the natural exponential function substitution using tools from algebraic geometry. The analysis shows that the multi-mode single-loop 7R spatial mechanism has three motion modes, including a 2-DOF planar 5R mode and two 1-DOF spatial 6R modes and can transit between each pair of motion modes through two transition configurations. The higher-order mobility analysis shows that the 7R mechanism has two-instantaneous DOF at a regular configuration of any motion mode and three instantaneous DOF in a transition configuration. The infinitesimal motions that are not tangential to finite motions are of second-order in transition configurations between 2-DOF motion mode 1 and 1-DOF motion modes 2 or 3 or first-order in transition configurations between 1-DOF motion modes 2 and 3.

Download Full-text

Variable degree-of-freedom spatial mechanisms composed of four circular translation joints

Journal of Mechanisms and Robotics ◽

10.1115/1.4050152 ◽

2021 ◽

pp. 1-16

Author(s):

Xianwen Kong

Keyword(s):

Algebraic Geometry ◽

Screw Theory ◽

Degree Of Freedom ◽

Variable Degree ◽

Circular Trajectory ◽

Spatial Mechanism ◽

Spatial Mechanisms ◽

Motion Modes ◽

Multi Mode ◽

Motion Mode

Abstract This paper deals with the construction and reconfiguration analysis of a spatial mechanism composed of four circular translation (G) joints. Two links connected by a G joint, which can be in different forms such as a planar parallelogram, translate along a circular trajectory with respect to each other. A spatial 4G mechanism, which is composed of four G joints, usually has 1-DOF (degree-of-freedom). Firstly, a 2-DOF spatial 4G mechanism is constructed. Then a novel variable-DOF spatial 4G mechanism is constructed starting from the 2-DOF 4G mechanism using the approach based on screw theory. Finally, the reconfiguration analysis is carried out in the configuration space using dual quaternions and tools from algebraic geometry. The analysis shows that the variable-DOF spatial 4G mechanism has one 2-DOF motion mode and one to two 1-DOF motion modes and reveals how the 4G mechanism can switch among these motion modes. By removing one link from two adjacent G joints each and two links from each of the remaining two G joints, we can obtain a queer-rectangle and a queer-parallelogram, which are the generalization of the queer-square or derivative queer-square in the literature. The approach in this paper can be extended to the analysis of other types of coupled mechanisms using cables and gears and multi-mode spatial mechanisms involving G joints.

Download Full-text

The research of dynamic impacts on the hydraulic structure foundation base, transformed in the process of accident recovery

MATEC Web of Conferences ◽

10.1051/matecconf/201825104040 ◽

2018 ◽

Vol 251 ◽

pp. 04040

Author(s):

Zaven Ter-Martirosyan ◽

Ivan Luzin

Keyword(s):

Field Experiments ◽

Dynamic Properties ◽

Soil Parameters ◽

Experimental Site ◽

Element Analysis ◽

The Finite Element Analysis ◽

Foundation Base ◽

Dynamic Impacts ◽

Scale Experiment ◽

Selection Of

The article presents the results of a comprehensive research of the dynamic impacts on a modified base. The modified base was obtained as a result of compensatory injection at the experimental site for the accident recovery at the hydraulic engineering structure. The complex study of the dynamic impacts includes special laboratory tests to determine the soil parameters, the finite element analysis of the experimental site, taking into account the dynamic properties, the selection of the necessary equipment for field experiments based on the numerical solution results, a full-scale experiment with the measurement of the foundation sediments of the experimental site.

Download Full-text

Monotonic Functions Method and Its Application to Staging of Patients with Prostate Cancer According to Pretreatment Data

Applied Sciences ◽

10.3390/app11093836 ◽

2021 ◽

Vol 11 (9) ◽

pp. 3836

Author(s):

Valeri Gitis ◽

Alexander Derendyaev ◽

Konstantin Petrov ◽

Eugene Yurkov ◽

Sergey Pirogov ◽

...

Keyword(s):

Prostate Cancer ◽

Learning Algorithm ◽

Binary Classification ◽

Preoperative Staging ◽

Threshold Value ◽

Logical Function ◽

Adequate Treatment ◽

Monotonic Functions ◽

Selection Of

Prostate cancer is the second most frequent malignancy (after lung cancer). Preoperative staging of PCa is the basis for the selection of adequate treatment tactics. In particular, an urgent problem is the classification of indolent and aggressive forms of PCa in patients with the initial stages of the tumor process. To solve this problem, we propose to use a new binary classification machine-learning method. The proposed method of monotonic functions uses a model in which the disease’s form is determined by the severity of the patient’s condition. It is assumed that the patient’s condition is the easier, the less the deviation of the indicators from the normal values inherent in healthy people. This assumption means that the severity (form) of the disease can be represented by monotonic functions from the values of the deviation of the patient’s indicators beyond the normal range. The method is used to solve the problem of classifying patients with indolent and aggressive forms of prostate cancer according to pretreatment data. The learning algorithm is nonparametric. At the same time, it allows an explanation of the classification results in the form of a logical function. To do this, you should indicate to the algorithm either the threshold value of the probability of successful classification of patients with an indolent form of PCa, or the threshold value of the probability of misclassification of patients with an aggressive form of PCa disease. The examples of logical rules given in the article show that they are quite simple and can be easily interpreted in terms of preoperative indicators of the form of the disease.

Download Full-text

Application of random forest algorithm for studying habitat selection of colonial herons and egrets in human-influenced landscapes

Ecological Research ◽

10.1007/s11284-014-1147-0 ◽

2014 ◽

Vol 29 (3) ◽

pp. 483-491 ◽

Cited By ~ 13

Author(s):

Luis Carrasco ◽

Miyuki Mashiko ◽

Yukihiko Toquenaga

Keyword(s):

Random Forest ◽

Habitat Selection ◽

Random Forest Algorithm ◽

Selection Of

Download Full-text

Machine learning, transcriptome, and genotyping chip analyses provide insights into SNP markers identifying flower color in Platycodon grandiflorus

Scientific Reports ◽

10.1038/s41598-021-87281-0 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Go-Eun Yu ◽

Younhee Shin ◽

Sathiyamoorthy Subramaniyam ◽

Sang-Ho Kang ◽

Si-Myung Lee ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Feature Selection Method ◽

Flower Color ◽

Classification Performance ◽

Snp Markers ◽

Rna Seq ◽

Color Classification ◽

Dna Pcr ◽

Selection Of

AbstractBellflower is an edible ornamental gardening plant in Asia. For predicting the flower color in bellflower plants, a transcriptome-wide approach based on machine learning, transcriptome, and genotyping chip analyses was used to identify SNP markers. Six machine learning methods were deployed to explore the classification potential of the selected SNPs as features in two datasets, namely training (60 RNA-Seq samples) and validation (480 Fluidigm chip samples). SNP selection was performed in sequential order. Firstly, 96 SNPs were selected from the transcriptome-wide SNPs using the principal compound analysis (PCA). Then, 9 among 96 SNPs were later identified using the Random forest based feature selection method from the Fluidigm chip dataset. Among six machines, the random forest (RF) model produced higher classification performance than the other models. The 9 SNP marker candidates selected for classifying the flower color classification were verified using the genomic DNA PCR with Sanger sequencing. Our results suggest that this methodology could be used for future selection of breeding traits even though the plant accessions are highly heterogeneous.

Download Full-text

Utilizing Data-Driven Models to Predict Brittleness in Tuscaloosa Marine Shale: A Machine Learning Approach

10.2118/208628-stu ◽

2021 ◽

Author(s):

Jamal Ahmadov

Keyword(s):

Machine Learning ◽

Random Forest ◽

Brittleness Index ◽

Estimation Methods ◽

Gradient Boosting ◽

Average Error ◽

Support Vector ◽

Marine Shale ◽

Effective Manner ◽

Selection Of

Abstract The Tuscaloosa Marine Shale (TMS) formation is a clay- and liquid-rich emerging shale play across central Louisiana and southwest Mississippi with recoverable resources of 1.5 billion barrels of oil and 4.6 trillion cubic feet of gas. The formation poses numerous challenges due to its high average clay content (50 wt%) and rapidly changing mineralogy, making the selection of fracturing candidates a difficult task. While brittleness plays an important role in screening potential intervals for hydraulic fracturing, typical brittleness estimation methods require the use of geomechanical and mineralogical properties from costly laboratory tests. Machine Learning (ML) can be employed to generate synthetic brittleness logs and therefore, may serve as an inexpensive and fast alternative to the current techniques. In this paper, we propose the use of machine learning to predict the brittleness index of Tuscaloosa Marine Shale from conventional well logs. We trained ML models on a dataset containing conventional and brittleness index logs from 8 wells. The latter were estimated either from geomechanical logs or log-derived mineralogy. Moreover, to ensure mechanical data reliability, dynamic-to-static conversion ratios were applied to Young's modulus and Poisson's ratio. The predictor features included neutron porosity, density and compressional slowness logs to account for the petrophysical and mineralogical character of TMS. The brittleness index was predicted using algorithms such as Linear, Ridge and Lasso Regression, K-Nearest Neighbors, Support Vector Machine (SVM), Decision Tree, Random Forest, AdaBoost and Gradient Boosting. Models were shortlisted based on the Root Mean Square Error (RMSE) value and fine-tuned using the Grid Search method with a specific set of hyperparameters for each model. Overall, Gradient Boosting and Random Forest outperformed other algorithms and showed an average error reduction of 5 %, a normalized RMSE of 0.06 and a R-squared value of 0.89. The Gradient Boosting was chosen to evaluate the test set and successfully predicted the brittleness index with a normalized RMSE of 0.07 and R-squared value of 0.83. This paper presents the practical use of machine learning to evaluate brittleness in a cost and time effective manner and can further provide valuable insights into the optimization of completion in TMS. The proposed ML model can be used as a tool for initial screening of fracturing candidates and selection of fracturing intervals in other clay-rich and heterogeneous shale formations.

Download Full-text