scholarly journals A Semi-Supervised Transfer Learning with Grid Segmentation for Outdoor Localization over LoRaWans

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2640
Author(s):  
Yuh-Shyan Chen ◽  
Chih-Shun Hsu ◽  
Chan-Yin Huang
Keyword(s):  
Transfer Learning ◽  
Outdoor Environment ◽  
Localization Algorithm ◽  
Target Domain ◽  
Location Accuracy ◽  
Localization Scheme ◽  
Signal Features ◽  
Unlabelled Data ◽  
Outdoor Localization ◽  
Relationship Of

During the training phase of the supervised learning, it is not feasible to collect all the datasets of labelled data in an outdoor environment for the localization problem. The semi-supervised transfer learning is consequently used to pre-train a small number of labelled data from the source domain to generate a kernel knowledge for the target domain. The kernel knowledge is transferred to a target domain to transfer some unlabelled data into the virtual labelled data. In this paper, we have proposed a new outdoor localization scheme using a semi-supervised transfer learning for LoRaWANs. In the proposed localization algorithm, a grid segmentation concept is proposed so as to generate a number of virtual labelled data through learning by constructing the relationship of labelled and unlabelled data. The labelled-unlabelled data relationship is repeatedly fine-tuned by correctly adding some more virtual labelled data. Basically, the more the virtual labelled data are added, the higher the location accuracy will be obtained. In the real implementation, three types of signal features, RSSI, SNR, and timestamps, are used for training to improve the location accuracy. The experimental results illustrate that the proposed scheme can improve the location accuracy and reduce the localization error as opposed to the existing outdoor localization schemes.

scholarly journals A Suppression Method of Concentration Background Noise by Transductive Transfer Learning for a Metal Oxide Semiconductor-Based Electronic Nose

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1913
Author(s):  
Huixiang Liu ◽  
Qing Li ◽  
Zhiyong Li ◽  
Yu Gu
Keyword(s):  
Transfer Learning ◽  
Environmental Changes ◽  
Oxide Semiconductor ◽  
Target Domain ◽  
Fisher Linear Discriminant ◽  
Linear Discriminant ◽  
Signal Features ◽  
Changes Over Time ◽  
Independence Criterion ◽  
Better Than

Signal drift caused by sensors or environmental changes, which can be regarded as data distribution changes over time, is related to transductive transfer learning, and the data in the target domain is not labeled. We propose a method that learns a subspace with maximum independence of the concentration features (MICF) according to the Hilbert-Schmidt Independence Criterion (HSIC), which reduces the inter-concentration discrepancy of distributions. Then, we use Iterative Fisher Linear Discriminant (IFLD) to extract the signal features by reducing the divergence within classes and increasing the divergence among classes, which helps to prevent inconsistent ratios of different types of samples among the domains. The effectiveness of MICF and IFLD was verified by three sets of experiments using sensors in real world conditions, along with experiments conducted in the authors’ laboratory. The proposed method achieved an accuracy of 76.17%, which was better than any of the existing methods that publish their data on a publicly available dataset (the Gas Sensor Drift Dataset). It was found that the MICF-IFLD was simple and effective, reduced interferences, and deftly managed tasks of transfer classification.

scholarly journals WSN Localization Algorithm on Underground Mining Area

2021 ◽  
Vol 23 (06) ◽  
pp. 464-475
Author(s):  
Shailendra Kumar Rawat ◽  
◽  
Dr. Prof. S. K. Singh ◽  
Dr. Ajay Kumar Bharti ◽  
◽  
...  
Keyword(s):  
Network Formation ◽  
Underground Mining ◽  
Research Work ◽  
Mining Area ◽  
Localization Algorithm ◽  
Mining Areas ◽  
Localization Scheme ◽  
Recent Developments ◽  
The Difference ◽  
Outdoor Localization

The main aim or goal of our research work is to localize the workers working in the mining area exactly or with minimum localization error. Network formation in mining areas is always very crucial. Laborers working in mining areas need strong availability of network as when they go down or deep in a mining area they can be rescued easily. It can only be possible when we know the exact location of the worker working in the particular area. For this, we need a better localization scheme. Many recent developments have been made in the field of the mining area. Random forest scheme, SVM-based regressive localization, Wi-Fi-based localization, and these are some schemes developed so far. RSSI and Trilateration work for both indoor and outdoor localization. The difference is only in terms of temperature because indoor temperature is different from outdoor temperature. When we are working on the basis of distance and signal strength then the proposed localization algorithm is suitable for hill areas too. From the results of the simulation, the new localization algorithm proposed in the paper with error checking and correction increases the accuracy of the localization in the X direction is 99.98 and in Y direction is 99.97 algorithms based on RSSI and dual prediction.

scholarly journals A Two-Phase Fashion Apparel Detection Method Based on YOLOv4

2021 ◽  
Vol 11 (9) ◽  
pp. 3782
Author(s):  
Chu-Hui Lee ◽  
Chen-Wei Lin
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Detection Method ◽  
Phase Transfer ◽  
Recognition Task ◽  
Phase Detection ◽  
Target Domain ◽  
Two Phase ◽  
Detection Technology ◽  
Fashion Apparel

Object detection is one of the important technologies in the field of computer vision. In the area of fashion apparel, object detection technology has various applications, such as apparel recognition, apparel detection, fashion recommendation, and online search. The recognition task is difficult for a computer because fashion apparel images have different characteristics of clothing appearance and material. Currently, fast and accurate object detection is the most important goal in this field. In this study, we proposed a two-phase fashion apparel detection method named YOLOv4-TPD (YOLOv4 Two-Phase Detection), based on the YOLOv4 algorithm, to address this challenge. The target categories for model detection were divided into the jacket, top, pants, skirt, and bag. According to the definition of inductive transfer learning, the purpose was to transfer the knowledge from the source domain to the target domain that could improve the effect of tasks in the target domain. Therefore, we used the two-phase training method to implement the transfer learning. Finally, the experimental results showed that the mAP of our model was better than the original YOLOv4 model through the two-phase transfer learning. The proposed model has multiple potential applications, such as an automatic labeling system, style retrieval, and similarity detection.

scholarly journals Deep Transfer Learning Method Based on 1D-CNN for Bearing Fault Diagnosis

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Jun He ◽  
Xiang Li ◽  
Yong Chen ◽  
Danfeng Chen ◽  
Jing Guo ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Learning Method ◽  
Target Domain ◽  
Source Domain ◽  
Second Order Statistics ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis

In mechanical fault diagnosis, it is impossible to collect massive labeled samples with the same distribution in real industry. Transfer learning, a promising method, is usually used to address the critical problem. However, as the number of samples increases, the interdomain distribution discrepancy measurement of the existing method has a higher computational complexity, which may make the generalization ability of the method worse. To solve the problem, we propose a deep transfer learning method based on 1D-CNN for rolling bearing fault diagnosis. First, 1-dimension convolutional neural network (1D-CNN), as the basic framework, is used to extract features from vibration signal. The CORrelation ALignment (CORAL) is employed to minimize marginal distribution discrepancy between the source domain and target domain. Then, the cross-entropy loss function and Adam optimizer are used to minimize the classification errors and the second-order statistics of feature distance between the source domain and target domain, respectively. Finally, based on the bearing datasets of Case Western Reserve University and Jiangnan University, seven transfer fault diagnosis comparison experiments are carried out. The results show that our method has better performance.

Low Cost Recursive Localization scheme for High Density Wireless Sensor Networks

2020 ◽  
pp. 263-285
Author(s):  
Badia Bouhdid ◽  
Wafa Akkari ◽  
Sofien Gannouni
Keyword(s):  
Low Cost ◽  
Cost Effective ◽  
High Density ◽  
Communication Overhead ◽  
Localization Algorithm ◽  
Localization Accuracy ◽  
Localization Scheme ◽  
Implementation Costs ◽  
Cost Effective Alternative ◽  
Algorithm Implementation

While existing localization approaches mainly focus on enhancing the accuracy, particular attention has recently been given to reducing the localization algorithm implementation costs. To obtain a tradeoff between location accuracy and implementation cost, recursive localization approaches are being pursued as a cost-effective alternative to the more expensive localization approaches. In the recursive approach, localization information increases progressively as new nodes compute their positions and become themselves reference nodes. A strategy is then required to control and maintain the distribution of these new reference nodes. The lack of such a strategy leads, especially in high density networks, to wasted energy, important communication overhead and even impacts the localization accuracy. In this paper, the authors propose an efficient recursive localization approach that reduces the energy consumption, the execution time, and the communication overhead, yet it increases the localization accuracy through an adequate distribution of reference nodes within the network.

Precise outdoor localization with a GPS–INS integration system

Robotica ◽  
2012 ◽  
Vol 31 (3) ◽  
pp. 371-379 ◽  
Author(s):  
Wonkyo Seo ◽  
Seoyoung Hwang ◽  
Jaehyun Park ◽  
Jang-Myung Lee
Keyword(s):  
Particle Filter ◽  
Discrete Wavelet ◽  
Signal Distortion ◽  
Localization Algorithm ◽  
Threshold Method ◽  
Variable Threshold ◽  
Unscented Particle Filter ◽  
Low Pass ◽  
Outdoor Localization ◽  
High Pass

SUMMARYThis paper proposes a precise outdoor localization algorithm with the integration of Global Positioning System (GPS) and Inertial Navigation System (INS). To achieve precise outdoor localization, two schemes are recently proposed, which consist of de-noising the INS signals and fusing the GPS and INS data. To reduce the noise from the internal INS sensors, the discrete wavelet transform and variable threshold method are utilized, and to fuse the GPS and INS data while filtering out the noise caused by the acceleration, deceleration, and unexpected slips, the Unscented Particle Filter (UPF) is adopted. Conventional de-noising methods mainly employ a combination of low-pass and high-pass filters, which results in signal distortion. This newly proposed system also utilizes the vibration information of the actuator according to the fluctuations of the velocity to minimize the signal distortion. The UPF resolves the nonlinearities of the actuator and non-normal distributions of the noise more effectively than the conventional particle filter (PF) or Extended Kalman Filter–PF. The superiority of the proposed algorithm was verified through experiments, and the results are reported.

An Enhanced DV-Hop Localization Algorithm for Wireless Sensor Networks

2012 ◽  
Vol 2 (2) ◽  
pp. 16-35 ◽  
Author(s):  
Shrawan Kumar ◽  
D. K. Lobiyal
Keyword(s):  
Wireless Sensor Networks ◽  
Linear Programming ◽  
Sensor Networks ◽  
Problem Formulation ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Localization Algorithm ◽  
Location Accuracy ◽  
Localization Accuracy ◽  
Error Terms

Obtaining precise location of sensor nodes at low energy consumption, less hardware requirement, and little computation is a challenging task. As one of the well-known range-free localization algorithm, DV-Hop can be simply implemented in wireless sensor networks, but it provides poor localization accuracy. Therefore, in this paper, the authors propose an enhanced DV-Hop localization algorithm that provides good localization accuracy without requiring additional hardware and communication messages in the network. The first two steps of proposed algorithm are similar to the respective steps of the DV-Hop algorithm. In the third step, they first separate error terms (correction factors) of the estimated distance between unknown node and anchor node. The authors then minimize these error terms by using linear programming to obtain better location accuracy. Furthermore, they enhance location accuracy of nodes by introducing weight matrix in the objective function of linear programming problem formulation. Simulation results show that the performance of our proposed algorithm is superior to DV-Hop algorithm and DV-Hop–based algorithms in all considered scenarios.

scholarly journals Underwater TDOA Acoustical Location Based on Majorization-Minimization Optimization

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4457
Author(s):  
Shuangshuang Li ◽  
Haixin Sun ◽  
Hamada Esmaiel
Keyword(s):  
Information Matrix ◽  
Initial Point ◽  
Auxiliary Function ◽  
Localization Algorithm ◽  
Underwater Acoustic ◽  
Acoustic Localization ◽  
Mm Algorithm ◽  
Localization Scheme ◽  
Localization Algorithms ◽  
Gradient Based

Underwater acoustic localization is a useful technique applied to any military and civilian applications. Among the range-based underwater acoustic localization methods, the time difference of arrival (TDOA) has received much attention because it is easy to implement and relatively less affected by the underwater environment. This paper proposes a TDOA-based localization algorithm for an underwater acoustic sensor network using the maximum-likelihood (ML) ratio criterion. To relax the complexity of the proposed localization complexity, we construct an auxiliary function, and use the majorization-minimization (MM) algorithm to solve it. The proposed localization algorithm proposed in this paper is called a T-MM algorithm. T-MM is applying the MM algorithm to the TDOA acoustic-localization technique. As the MM algorithm iterations are sensitive to the initial points, a gradient-based initial point algorithm is used to set the initial points of the T-MM scheme. The proposed T-MM localization scheme is evaluated based on squared position error bound (SPEB), and through calculation, we get the SPEB expression by the equivalent Fisher information matrix (EFIM). The simulation results show how the proposed T-MM algorithm has better performance and outperforms the state-of-the-art localization algorithms in terms of accuracy and computation complexity even under a high presence of underwater noise.

scholarly journals PTP1B Modulates the Association of β-Catenin with N-cadherin through Binding to an Adjacent and Partially Overlapping Target Site

2002 ◽  
Vol 277 (51) ◽  
pp. 49989-49997 ◽  
Author(s):  
Gang Xu ◽  
Carlos Arregui ◽  
Jack Lilien ◽  
Janne Balsamo
Keyword(s):  
Amino Acids ◽  
Cell Surface ◽  
Tyrosine Phosphatase ◽  
Target Site ◽  
Target Domain ◽  
Chick Retina ◽  
Cell Permeable Peptide ◽  
A Cell ◽  
Relationship Of

The nonreceptor tyrosine phosphatase PTP1B associates with the cytoplasmic domain of N-cadherin and may regulate cadherin function through dephosphorylation of β-catenin. We have now identified the domain on N-cadherin to which PTP1B binds and characterized the effect of perturbing this domain on cadherin function. Deletion constructs lacking amino acids 872–891 fail to bind PTP1B. This domain partially overlaps with the β-catenin binding domain. To further define the relationship of these two sites, we used peptides to competein vitrobinding. A peptide representing the most NH2-terminal 8 amino acids of the PTP1B binding site, the region of overlap with the β-catenin target, effectively competes for binding of β-catenin but is much less effective in competing PTP1B, whereas two peptides representing the remaining 12 amino acids have no effect on β-catenin binding but effectively compete for PTP1B binding. Introduction into embryonic chick retina cells of a cell-permeable peptide mimicking the 8 most COOH-terminal amino acids in the PTP1B target domain, the region most distant from the β-catenin target site, prevents binding of PTP1B, increases the pool of free, tyrosine-phosphorylated β-catenin, and results in loss of N-cadherin function. N-cadherin lacking this same region of the PTP1B target site does not associate with PTP1B or β-catenin and is not efficiently expressed at the cell surface of transfected L cells. Thus, interaction of PTP1B with N-cadherin is essential for its association with β-catenin, stable expression at the cell surface, and consequently, cadherin function.

scholarly journals A Study of Visual Descriptors for Outdoor Navigation Using Google Street View Images

2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
L. Fernández ◽  
L. Payá ◽  
O. Reinoso ◽  
L. M. Jiménez ◽  
M. Ballesta
Keyword(s):  
Visual Information ◽  
Visual Navigation ◽  
Urban Environments ◽  
Outdoor Environment ◽  
Localization Algorithm ◽  
Google Street View ◽  
Street View ◽  
Visual Descriptors ◽  
Outdoor Environments ◽  
Panoramic Images

A comparative analysis between several methods to describe outdoor panoramic images is presented. The main objective consists in studying the performance of these methods in the localization process of a mobile robot (vehicle) in an outdoor environment, when a visual map that contains images acquired from different positions of the environment is available. With this aim, we make use of the database provided by Google Street View, which contains spherical panoramic images captured in urban environments and their GPS position. The main benefit of using these images resides in the fact that it permits testing any novel localization algorithm in countless outdoor environments anywhere in the world and under realistic capture conditions. The main contribution of this work consists in performing a comparative evaluation of different methods to describe images to solve the localization problem in an outdoor dense map using only visual information. We have tested our algorithms using several sets of panoramic images captured in different outdoor environments. The results obtained in the work can be useful to select an appropriate description method for visual navigation tasks in outdoor environments using the Google Street View database and taking into consideration both the accuracy in localization and the computational efficiency of the algorithm.

Sign in / Sign up

Export Citation Format

Share Document