A Novel Sparse Representation and Softmax Method for Human Activity Identification in Healthcare Systems

Human activity identification has been attracting extensive research attention due to its prominent applications in healthcare systems such as healthcare monitoring and rehabilitation process. Traditional methods are greatly dependent on hand-crafted feature extraction, hampering their generalization performance. In this research, a novel sparse representation and softmax (SRS) method is presented for human activity identification to reduce the computation complexity of the task and improve the accuracy of classification. The multi-class classifier based on the softmax function is firstly introduced to improve sensor data classification performance. Sparse representation technology is then applied in our work to extract human activity features from sensor data. The output of the classifier model, taking raw sensor data after transforming into a high-dimensional feature space as input, provides a normalization of the probability distribution of activity categories, thereby ensuring accuracy and efficiency under diverse human activities. Experiments on a collection of raw sensor data from wireless sensor networks demonstrate the identification accuracy of our approach compared with nearest neighbor, naive Bayesian classifier, and support vector machine methods. The F1-score of the proposed method is respectively 14.1%, 19.6%, and 6.8% higher than the approaches mentioned above, indicating the effectiveness of SRS.

Download Full-text

Fusion of smartphone sensor data for classification of daily user activities

Multimedia Tools and Applications ◽

10.1007/s11042-021-11105-6 ◽

2021 ◽

Author(s):

Gökhan Şengül ◽

Erol Ozcelik ◽

Sanjay Misra ◽

Robertas Damaševičius ◽

Rytis Maskeliūnas

Keyword(s):

Nearest Neighbor ◽

Feature Fusion ◽

Classification Performance ◽

Sensor Data ◽

Stochastic Gradient Descent ◽

Optimal Decision ◽

Support Vector ◽

K Nearest Neighbor ◽

Gradient Descent Algorithm ◽

User Activities

AbstractNew mobile applications need to estimate user activities by using sensor data provided by smart wearable devices and deliver context-aware solutions to users living in smart environments. We propose a novel hybrid data fusion method to estimate three types of daily user activities (being in a meeting, walking, and driving with a motorized vehicle) using the accelerometer and gyroscope data acquired from a smart watch using a mobile phone. The approach is based on the matrix time series method for feature fusion, and the modified Better-than-the-Best Fusion (BB-Fus) method with a stochastic gradient descent algorithm for construction of optimal decision trees for classification. For the estimation of user activities, we adopted a statistical pattern recognition approach and used the k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers. We acquired and used our own dataset of 354 min of data from 20 subjects for this study. We report a classification performance of 98.32 % for SVM and 97.42 % for kNN.

Download Full-text

Binary Spectrum Feature for Improved Classiﬁer Performance

10.36227/techrxiv.12993122 ◽

2020 ◽

Author(s):

Nalika Ulapane ◽

Karthick Thiyagarajan ◽

sarath kodagoda

Keyword(s):

Machine Learning ◽

Classification Performance ◽

Feature Reduction ◽

Sensor Data ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Monitoring Task ◽

Classifier Performance ◽

Spectrum Feature

<div>Classiﬁcation has become a vital task in modern machine learning and Artiﬁcial Intelligence applications, including smart sensing. Numerous machine learning techniques are available to perform classiﬁcation. Similarly, numerous practices, such as feature selection (i.e., selection of a subset of descriptor variables that optimally describe the output), are available to improve classiﬁer performance. In this paper, we consider the case of a given supervised learning classiﬁcation task that has to be performed making use of continuous-valued features. It is assumed that an optimal subset of features has already been selected. Therefore, no further feature reduction, or feature addition, is to be carried out. Then, we attempt to improve the classiﬁcation performance by passing the given feature set through a transformation that produces a new feature set which we have named the “Binary Spectrum”. Via a case study example done on some Pulsed Eddy Current sensor data captured from an infrastructure monitoring task, we demonstrate how the classiﬁcation accuracy of a Support Vector Machine (SVM) classiﬁer increases through the use of this Binary Spectrum feature, indicating the feature transformation’s potential for broader usage.</div><div><br></div>

Download Full-text

Feature and Decision Level Fusion in Children Multimodal Biometrics

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.e6396.018520 ◽

2020 ◽

Vol 8 (5) ◽

pp. 2522-2527

Keyword(s):

Nearest Neighbor ◽

Principal Component ◽

Identification Accuracy ◽

Support Vector ◽

Biometric System ◽

K Nearest Neighbor ◽

Decision Level ◽

Multimodal Biometric System ◽

Decision Level Fusion ◽

Level Fusion

In this paper, we design method for recognition of fingerprint and IRIS using feature level fusion and decision level fusion in Children multimodal biometric system. Initially, Histogram of Gradients (HOG), Gabour and Maximum filter response are extracted from both the domains of fingerprint and IRIS and considered for identification accuracy. The combination of feature vector of all the possible features is recommended by biometrics traits of fusion. For fusion vector the Principal Component Analysis (PCA) is used to select features. The reduced features are fed into fusion classifier of K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Navie Bayes(NB). For children multimodal biometric system the suitable combination of features and fusion classifiers is identified. The experimentation conducted on children’s fingerprint and IRIS database and results reveal that fusion combination outperforms individual. In addition the proposed model advances the unimodal biometrics system.

Download Full-text

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

Sensors ◽

10.3390/s19122814 ◽

2019 ◽

Vol 19 (12) ◽

pp. 2814 ◽

Cited By ~ 2

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.

Download Full-text

Kernel Joint Sparse Representation Based on Self-Paced Learning for Hyperspectral Image Classification

Remote Sensing ◽

10.3390/rs11091114 ◽

2019 ◽

Vol 11 (9) ◽

pp. 1114

Author(s):

Sixiu Hu ◽

Jiangtao Peng ◽

Yingxiong Fu ◽

Luoqing Li

Keyword(s):

Sparse Representation ◽

Hyperspectral Image ◽

Feature Space ◽

Classification Performance ◽

Hyperspectral Data ◽

Data Sets ◽

Neighborhood Structure ◽

Joint Sparse Representation ◽

Negative Effect ◽

Sparse Coefficient

By means of joint sparse representation (JSR) and kernel representation, kernel joint sparse representation (KJSR) models can effectively model the intrinsic nonlinear relations of hyperspectral data and better exploit spatial neighborhood structure to improve the classification performance of hyperspectral images. However, due to the presence of noisy or inhomogeneous pixels around the central testing pixel in the spatial domain, the performance of KJSR is greatly affected. Motivated by the idea of self-paced learning (SPL), this paper proposes a self-paced KJSR (SPKJSR) model to adaptively learn weights and sparse coefficient vectors for different neighboring pixels in the kernel-based feature space. SPL strateges can learn a weight to indicate the difficulty of feature pixels within a spatial neighborhood. By assigning small weights for unimportant or complex pixels, the negative effect of inhomogeneous or noisy neighboring pixels can be suppressed. Hence, SPKJSR is usually much more robust. Experimental results on Indian Pines and Salinas hyperspectral data sets demonstrate that SPKJSR is much more effective than traditional JSR and KJSR models.

Download Full-text

Finer Resolution Mapping of Marine Aquaculture Areas Using WorldView-2 Imagery and a Hierarchical Cascade Convolutional Neural Network

Remote Sensing ◽

10.3390/rs11141678 ◽

2019 ◽

Vol 11 (14) ◽

pp. 1678 ◽

Cited By ~ 3

Author(s):

Yongyong Fu ◽

Ziran Ye ◽

Jinsong Deng ◽

Xinyu Zheng ◽

Yibo Huang ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Contextual Information ◽

Feature Space ◽

Classification Performance ◽

Support Vector ◽

Marine Resources ◽

Marine Aquaculture ◽

Multi Scale ◽

Coastal Marine

Marine aquaculture plays an important role in seafood supplement, economic development, and coastal ecosystem service provision. The precise delineation of marine aquaculture areas from high spatial resolution (HSR) imagery is vital for the sustainable development and management of coastal marine resources. However, various sizes and detailed structures of marine objects make it difficult for accurate mapping from HSR images by using conventional methods. Therefore, this study attempts to extract marine aquaculture areas by using an automatic labeling method based on the convolutional neural network (CNN), i.e., an end-to-end hierarchical cascade network (HCNet). Specifically, for marine objects of various sizes, we propose to improve the classification performance by utilizing multi-scale contextual information. Technically, based on the output of a CNN encoder, we employ atrous convolutions to capture multi-scale contextual information and aggregate them in a hierarchical cascade way. Meanwhile, for marine objects with detailed structures, we propose to refine the detailed information gradually by using a series of long-span connections with fine resolution features from the shallow layers. In addition, to decrease the semantic gaps between features in different levels, we propose to refine the feature space (i.e., channel and spatial dimensions) using an attention-based module. Experimental results show that our proposed HCNet can effectively identify and distinguish different kinds of marine aquaculture, with 98% of overall accuracy. It also achieves better classification performance compared with object-based support vector machine and state-of-the-art CNN-based methods, such as FCN-32s, U-Net, and DeeplabV2. Our developed method lays a solid foundation for the intelligent monitoring and management of coastal marine resources.

Download Full-text

A Benchmark of Data Stream Classification for Human Activity Recognition on Connected Objects

Sensors ◽

10.3390/s20226486 ◽

2020 ◽

Vol 20 (22) ◽

pp. 6486

Author(s):

Martin Khannouz ◽

Tristan Glatard

Keyword(s):

Activity Recognition ◽

Human Activity ◽

Data Stream ◽

Nearest Neighbor ◽

Human Activity Recognition ◽

Classification Performance ◽

Resource Consumption ◽

Stream Classification ◽

The Real ◽

Hoeffding Tree

This paper evaluates data stream classifiers from the perspective of connected devices, focusing on the use case of Human Activity Recognition. We measure both the classification performance and resource consumption (runtime, memory, and power) of five usual stream classification algorithms, implemented in a consistent library, and applied to two real human activity datasets and three synthetic datasets. Regarding classification performance, the results show the overall superiority of the Hoeffding Tree, the Mondrian forest, and the Naïve Bayes classifiers over the Feedforward Neural Network and the Micro Cluster Nearest Neighbor classifiers on four datasets out of six, including the real ones. In addition, the Hoeffding Tree and—to some extent—the Micro Cluster Nearest Neighbor, are the only classifiers that can recover from a concept drift. Overall, the three leading classifiers still perform substantially worse than an offline classifier on the real datasets. Regarding resource consumption, the Hoeffding Tree and the Mondrian forest are the most memory intensive and have the longest runtime; however, no difference in power consumption is found between classifiers. We conclude that stream learning for Human Activity Recognition on connected objects is challenged by two factors which could lead to interesting future work: a high memory consumption and low F1 scores overall.

Download Full-text

Comparative analysis of breast cancer detection in mammograms and thermograms

Biomedical Engineering / Biomedizinische Technik ◽

10.1515/bmt-2014-0047 ◽

2015 ◽

Vol 60 (1) ◽

Cited By ~ 7

Author(s):

Marina Milosevic ◽

Dragan Jankovic ◽

Aleksandar Peulic

Keyword(s):

Nearest Neighbor ◽

Region Of Interest ◽

Texture Features ◽

Classification Performance ◽

Support Vector ◽

K Nearest Neighbor ◽

Characteristic Analysis ◽

Analysis Society ◽

Fold Cross Validation ◽

Neighbor Classifier

AbstractIn this paper, we present a system based on feature extraction techniques for detecting abnormal patterns in digital mammograms and thermograms. A comparative study of texture-analysis methods is performed for three image groups: mammograms from the Mammographic Image Analysis Society mammographic database; digital mammograms from the local database; and thermography images of the breast. Also, we present a procedure for the automatic separation of the breast region from the mammograms. Computed features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from the region of interest. The ability of feature set in differentiating abnormal from normal tissue is investigated using a support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross-validation method and receiver operating characteristic analysis was performed.

Download Full-text

Fault Diagnosis for Rolling Element Bearings Based on Feature Space Reconstruction and Multiscale Permutation Entropy

Entropy ◽

10.3390/e21050519 ◽

2019 ◽

Vol 21 (5) ◽

pp. 519 ◽

Cited By ~ 6

Author(s):

Weibo Zhang ◽

Jianzhong Zhou

Keyword(s):

Diagnostic Algorithm ◽

Feature Space ◽

Vibration Signal ◽

Rolling Bearing ◽

Ensemble Empirical Mode Decomposition ◽

Classification Performance ◽

Fault Classification ◽

Permutation Entropy ◽

Support Vector ◽

Intrinsic Mode Functions

Aimed at distinguishing different fault categories of severity of rolling bearings, a novel method based on feature space reconstruction and multiscale permutation entropy is proposed in the study. Firstly, the ensemble empirical mode decomposition algorithm (EEMD) was employed to adaptively decompose the vibration signal into multiple intrinsic mode functions (IMFs), and the representative IMFs which contained rich fault information were selected to reconstruct a feature vector space. Secondly, the multiscale permutation entropy (MPE) was used to calculate the complexity of reconstructed feature space. Finally, the value of multiscale permutation entropy was presented to a support vector machine for fault classification. The proposed diagnostic algorithm was applied to three groups of rolling bearing experiments. The experimental results indicate that the proposed method has better classification performance and robustness than other traditional methods.

Download Full-text

DETERMINATION OF OPTIMUM CLASSIFICATION SYSTEM FOR HYPERSPECTRAL IMAGERY AND LIDAR DATA BASED ON BEES ALGORITHM

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsarchives-xl-1-w5-651-2015 ◽

2015 ◽

Vol XL-1-W5 ◽

pp. 651-656

Author(s):

F. Samadzadega ◽

H. Hasani

Keyword(s):

Urban Area ◽

Hyperspectral Imagery ◽

Feature Space ◽

Classification Performance ◽

Feature Subset Selection ◽

Bees Algorithm ◽

Support Vector ◽

Svm Classifier ◽

Lidar Data ◽

Feature Subset

Hyperspectral imagery is a rich source of spectral information and plays very important role in discrimination of similar land-cover classes. In the past, several efforts have been investigated for improvement of hyperspectral imagery classification. Recently the interest in the joint use of LiDAR data and hyperspectral imagery has been remarkably increased. Because LiDAR can provide structural information of scene while hyperspectral imagery provide spectral and spatial information. The complementary information of LiDAR and hyperspectral data may greatly improve the classification performance especially in the complex urban area. In this paper feature level fusion of hyperspectral and LiDAR data is proposed where spectral and structural features are extract from both dataset, then hybrid feature space is generated by feature stacking. Support Vector Machine (SVM) classifier is applied on hybrid feature space to classify the urban area. In order to optimize the classification performance, two issues should be considered: SVM parameters values determination and feature subset selection. Bees Algorithm (BA) is powerful meta-heuristic optimization algorithm which is applied to determine the optimum SVM parameters and select the optimum feature subset simultaneously. The obtained results show the proposed method can improve the classification accuracy in addition to reducing significantly the dimension of feature space.

Download Full-text