scholarly journals Wireless Indoor Localization Using Convolutional Neural Network and Gaussian Process Regression

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2508 ◽  
Author(s):  
Guolong Zhang ◽  
Ping Wang ◽  
Haibing Chen ◽  
Lan Zhang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Gaussian Process ◽  
Hybrid Model ◽  
Nearest Neighbor ◽  
Gaussian Process Regression ◽  
Kernel Functions ◽  
Training Dataset ◽  
K Nearest Neighbor ◽  
Positive Effects

This paper presents a localization model employing convolutional neural network (CNN) and Gaussian process regression (GPR) based on Wi-Fi received signal strength indication (RSSI) fingerprinting data. In the proposed scheme, the CNN model is trained by a training dataset. The trained model adapts to complex scenes with multipath effects or many access points (APs). More specifically, the pre-processing algorithm makes the RSSI vector which is formed by considerable RSSI values from different APs readable by the CNN algorithm. The trained CNN model improves the positioning performance by taking a series of RSSI vectors into account and extracting local features. In this design, however, the performance is to be further improved by applying the GPR algorithm to adjust the coordinates of target points and offset the over-fitting problem of CNN. After implementing the hybrid model, the model is experimented with a public database that was collected from a library of Jaume I University in Spain. The results show that the hybrid model has outperformed the model using k-nearest neighbor (KNN) by 61.8%. While the CNN model improves the performance by 45.8%, the GPR algorithm further enhances the localization accuracy. In addition, the paper has also experimented with the three kernel functions, all of which have been demonstrated to have positive effects on GPR.

scholarly journals A New Approach to Fall Detection Based on Improved Dual Parallel Channels Convolutional Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2814 ◽  
Author(s):  
Xiaoguang Liu ◽  
Huanliang Li ◽  
Cunguang Lou ◽  
Tie Liang ◽  
Xiuling Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Nearest Neighbor ◽  
Fall Detection ◽  
Classification Performance ◽  
Daily Activities ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Linear Discriminant ◽  
Parallel Channels

Falls are the major cause of fatal and non-fatal injury among people aged more than 65 years. Due to the grave consequences of the occurrence of falls, it is necessary to conduct thorough research on falls. This paper presents a method for the study of fall detection using surface electromyography (sEMG) based on an improved dual parallel channels convolutional neural network (IDPC-CNN). The proposed IDPC-CNN model is designed to identify falls from daily activities using the spectral features of sEMG. Firstly, the classification accuracy of time domain features and spectrograms are compared using linear discriminant analysis (LDA), k-nearest neighbor (KNN) and support vector machine (SVM). Results show that spectrograms provide a richer way to extract pattern information and better classification performance. Therefore, the spectrogram features of sEMG are selected as the input of IDPC-CNN to distinguish between daily activities and falls. Finally, The IDPC-CNN is compared with SVM and three different structure CNNs under the same conditions. Experimental results show that the proposed IDPC-CNN achieves 92.55% accuracy, 95.71% sensitivity and 91.7% specificity. Overall, The IDPC-CNN is more effective than the comparison in accuracy, efficiency, training and generalization.

scholarly journals Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional Neural Network

2018 ◽  
Vol 8 (8) ◽  
pp. 1346 ◽  
Author(s):  
Ping Zhou ◽  
Gongbo Zhou ◽  
Zhencai Zhu ◽  
Chaoquan Tang ◽  
Zhenzhi He ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Health Monitoring ◽  
Nearest Neighbor ◽  
Back Propagation ◽  
Feature Space ◽  
Batch Size ◽  
K Nearest Neighbor ◽  
Hoisting System

With the arrival of the big data era, it has become possible to apply deep learning to the health monitoring of mine production. In this paper, a convolutional neural network (CNN)-based method is proposed to monitor the health condition of the balancing tail ropes (BTRs) of the hoisting system, in which the feature of the BTR image is adaptively extracted using a CNN. This method can automatically detect various BTR faults in real-time, including disproportional spacing, twisted rope, broken strand and broken rope faults. Firstly, a CNN structure is proposed, and regularization technology is adopted to prevent overfitting. Then, a method of image dataset description and establishment that can cover the entire feature space of overhanging BTRs is put forward. Finally, the CNN and two traditional data mining algorithms, namely, k-nearest neighbor (KNN) and an artificial neural network with back propagation (ANN-BP), are adopted to train and test the established dataset, and the influence of hyperparameters on the network diagnostic accuracy is investigated experimentally. The experimental results showed that the CNN could effectively avoid complex steps such as manual feature extraction, that the learning rate and batch-size strongly affected the accuracy and training efficiency, and that the fault diagnosis accuracy of CNN was 100%, which was higher than that of KNN and ANN-BP. Therefore, the proposed CNN with high accuracy, real-time functioning and generalization performance is suitable for application in the health monitoring of hoisting system BTRs.

scholarly journals Recognition and Classification of Incipient Cable Failures Based on Variational Mode Decomposition and a Convolutional Neural Network

Energies ◽  
2019 ◽  
Vol 12 (10) ◽  
pp. 2005 ◽  
Author(s):  
Jiaying Deng ◽  
Wenhai Zhang ◽  
Xiaomei Yang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Bp Neural Network ◽  
Nearest Neighbor ◽  
Feature Vector ◽  
Support Vector ◽  
Variational Mode Decomposition ◽  
K Nearest Neighbor ◽  
Mode Decomposition

To avoid power supply hazards caused by cable failures, this paper presents an approach of incipient cable failure recognition and classification based on variational mode decomposition (VMD) and a convolutional neural network (CNN). By using VMD, the original current signal is decomposed into seven modes with different center frequencies. Then, 42 features are extracted for the seven modes and used to construct a feature vector as input of the CNN to classify incipient cable failure through deep learning. Compared with using the original signals directly as the CNN input, the proposed approach is more efficient and robust. Experiments on different classifiers, namely, the decision tree (DT), K-nearest neighbor (KNN), BP neural network (BP) and support vector machine (SVM), and show that the CNN outperforms the other classifiers in terms of accuracy.

scholarly journals Deep Nearest Neighbor Website Fingerprinting Attack Technology

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Maohua Guo ◽  
Jinlong Fei ◽  
Yitong Meng
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Research Methods ◽  
Classification Accuracy ◽  
Nearest Neighbor ◽  
Concept Drift ◽  
Small Sample ◽  
K Nearest Neighbor ◽  
Encrypted Traffic ◽  
Fingerprinting Attack

By website fingerprinting (WF) technologies, local listeners are enabled to track the specific website visited by users through an investigation of the encrypted traffic between the users and the Tor network entry node. The current triplet fingerprinting (TF) technique proved the possibility of small sample WF attacks. Previous research methods only concentrate on extracting the overall features of website traffic while ignoring the importance of website local fingerprinting characteristics for small sample WF attacks. Thus, in the present paper, a deep nearest neighbor website fingerprinting (DNNF) attack technology is proposed. The deep local fingerprinting features of websites are extracted via the convolutional neural network (CNN), and then the k-nearest neighbor (k-NN) classifier is utilized to classify the prediction. When the website provides only 20 samples, the accuracy can reach 96.2%. We also found that the DNNF method acts well compared to the traditional methods in coping with transfer learning and concept drift problems. In comparison to the TF method, the classification accuracy of the proposed method is improved by 2%–5% and it is only dropped by 3% when classifying the data collected from the same website after two months. These experiments revealed that the DNNF is a more flexible, efficient, and robust website fingerprinting attack technology, and the local fingerprinting features of websites are particularly important for small sample WF attacks.

scholarly journals Image classification of malaria using hybrid algorithms: convolutional neural network and method to find appropriate K for K-nearest neighbor

2019 ◽  
Vol 16 (1) ◽  
pp. 382
Author(s):  
Wisit Lumchanow ◽  
Sakol Udomsiri
Keyword(s):  
Neural Network ◽  
Plasmodium Falciparum ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Plasmodium Vivax ◽  
Nearest Neighbor ◽  
Learning Rate ◽  
K Nearest Neighbor ◽  
Ring Form

<span>This paper presents image classification algorithms to improve the learning rate and to comparison the classification efficiency. Using convolutional neural network (CNN) for feature extraction and method to find appropriate k for k-nearest neighbor (KNN). Medical datasets were used in the experiments to classify <span>Plasmodium Vivax and Plasmodium Falciparum. Results of the study indicated that for Plasmodium Vivax in ring form, the appropriate k was 1 and the learning rate (LR) was 83.33%, Trophozoite (k=5, LR=91.67%),</span></span><span> Schizont (k=1, LR=83.33<span>%</span>), and Gametocyte (k=1, LR=<span lang="AR-SA" dir="RTL">91.67</span><span>%</span>) whereas </span><span>Plasmodium Falciparum in ring form</span><span> (k=7, LR=91.67%)<span>,</span> Trophozoite (k=1, LR=83.33%), Schizont (k=1, LR=91.67%) and Gametocyte (k=1, LR=100%).</span>

scholarly journals Cloud-based architecture for face identification with deep learning using convolutional neural network

2021 ◽  
Vol 23 (2) ◽  
pp. 811
Author(s):  
Aditya Herlambang ◽  
Putu Wira Buana ◽  
I Nyoman Piarsa
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Nearest Neighbor ◽  
Face Identification ◽  
K Nearest Neighbor ◽  
Non Invasive ◽  
The Face ◽  
And Performance ◽  
University Of Manchester

The use of a face as a biometric to identify a person in order to keep the system safe from an unauthorized person has advantages over other biometric characteristics. The face as a biometric has more structure and a wider area than other biometrics, while can be retrieved in a non-invasive manner. We proposed a cloud-based architecture for face identification with deep learning using convolutional neural network. Face identification in this study used a cloud-based engine with four stages, namely face detection with histogram of oriented gradients (HOG), image enhancement, feature extraction using convolutional neural network, and classification using k-nearest neighbor (KNN), SVM, as well as random forest algorithm. This study conducted a classification experiment with cloud-based architecture using three different datasets, namely Faces94, Faces96 and University of Manchester Institute of Science and Technology (UMIST) face dataset. The results from this study are with the proposed cloud-based architecture, the best accuracy is obtained by KNN algorithm with an accuracy of 99% on Faces94 dataset, 99% accuracy on Faces96 dataset, 97% on UMIST face dataset, and performance of the three algorithms decreased in UMIST face dataset with facial variations from various angles from left to right profile.

scholarly journals Deep Convolutional neural network (CNN) in tea leaf chlorophyll estimation: A new direction of modern tea farming in Assam, India

2021 ◽  
Vol 13 (3) ◽  
pp. 1059-1064
Author(s):  
Utpal Barman
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Nearest Neighbor ◽  
Light Condition ◽  
Absolute Error ◽  
Small Scale ◽  
K Nearest Neighbor ◽  
Leaf Chlorophyll ◽  
Colour Features ◽  
Tea Leaf

This study presents the uprising of leaf chlorophyll estimation from traditional mechanical method to machine learning-based method. Earlier chlorophyll estimation techniques such as Spectrophotometer and Soil Plant Analysis Development (SPAD) meter demand cost, time, labour, skill, and expertise. A small-scale tea farmer may not afford these devices. The present study reports a low-cost digital method to predict the tea leaf chlorophyll using 1-D Convolutional Neural Network (1-D CNN). After capturing the tea leaf images using a digital camera in a natural light condition, a total of 12 different colour features were extracted from tea leaf images. A SPAD was used to estimate the original chlorophyll value of the tea leaves. The paper shows the correlation of original tea leaf chlorophyll with the extracted colour features of the tea leaf images. Apart from 1-D CNN, the Multiple Linear Regression (MLR) and K-Nearest Neighbor (KNN) were also applied to predict the tea leaf chlorophyll and compared their results with the 1-D CNN. The 1-D CNN model outperformed with an accuracy of 81.1%, Mean Absolute Error (MAE) of 3.01, and Root Mean Square Error (RMSE) of 4.18. The investigation system is very simple and cost-effective. It can be used in tea farming as a digital SPAD for faster and accurate leaf chlorophyll estimation in an easy way.

Sign in / Sign up

Export Citation Format

Share Document