Adaptive Activity Recognition with Dynamic Heterogeneous Sensor Fusion

In recent years, a variety of manifold-based learning dimensionality reduction techniques have been proposed, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. Among them, marginal fisher analysis (MFA) achieved high performance for face recognition. However, the optimal basis vectors obtained by MFA are non-orthogonal and MFA usually deteriorates when labeled information is insufficient. In order to resolve these problems, we present a new method called orthogonal semi-supervised marginal fisher analysis (OSMFA), which not only extracts all the orthogonal discriminant vectors but also preserves the global structure of labeled and unlabeled samples to learn a better subspace for classification. Experimental results on ORL database demonstrate the effectiveness of the proposed algorithm.

Marginal Fisher analysis (MFA) exploits the margin criterion to compact the intraclass data and separate the interclass data, and it is very useful to analyze the high-dimensional data. However, MFA just considers the structure relationships of neighbor points, and it cannot effectively represent the intrinsic structure of hyperspectral imagery (HSI) that possesses many homogenous areas. In this paper, we propose a new dimensionality reduction (DR) method, termed local geometric structure Fisher analysis (LGSFA), for HSI classification. Firstly, LGSFA uses the intraclass neighbor points of each point to compute its reconstruction point. Then, an intrinsic graph and a penalty graph are constructed to reveal the intraclass and interclass properties of hyperspectral data. Finally, the neighbor points and corresponding intraclass reconstruction points are used to enhance the intraclass-manifold compactness and the interclass-manifold separability. LGSFA can effectively reveal the intrinsic manifold structure and obtain the discriminating features of HSI data for classification. Experiments on the Salinas, Indian Pines, and Urban data sets show that the proposed LGSFA algorithm achieves the best classification results than other state-of-the-art methods.

The recently proposed Marginal Fisher Analysis (MFA) achieved high performance for face recognition. However, MFA suffers from the small sample size problem and the optimal basis vectors obtained by the MFA are nonorthogonal. In this paper, we present a new method called Direct Orthogonal Marginal Fisher Analysis (DOMFA), which is able to extract all the orthogonal discriminant vectors simultaneously in the high-dimensional feature space without pre-processing using PCA and does not suffer the small sample size problem. Experimental results on ORL database indicate that the proposed DOMFA method achieves better recognition rate than the MFA method and some other orthogonal feature extraction algorithms.

Subspace learning based face recognition methods have attracted considerable interests in recent years, including principal component analysis (PCA), linear discriminant analysis (LDA), locality preserving projection (LPP), neighborhood preserving embedding (NPE) and marginal Fisher analysis (MFA). However, a disadvantage of all these approaches is that their computations involve eigen- decomposition of dense matrices which is expensive in both time and memory. In this paper, we propose a novel dimensionality reduction framework, called spectral regression (SR), for efficient regularized subspace learning. SR casts the problem of learning the projective functions into a regression framework, which avoids eigen-decomposition of dense matrices. Also, with the regression based framework, different kinds of regularizes can be naturally incorporated into our algorithm which makes it more flexible. Computational analysis shows that SR has only linear-time complexity which is a huge speed up comparing to the cubic-time complexity of the ordinary approaches. Experimental results on face recognition demonstrate the effectiveness and efficiency of our method.

Decision support system for fatty liver disease using GIST descriptors extracted from ultrasound images

This paper presents a novel marginal Fisher regression classification (MFRC) method by incorporating the ideas of marginal Fisher analysis (MFA) and linear regression classification (LRC). The MFRC aims at minimizing the within-class compactness over the between-class separability to find an optimal embedding matrix for the LRC so that the LRC on that subspace achieves a high discrimination for classification. Specifically, the within-class compactness is measured with the sum of distances between each sample and its neighbors within the same class with the LRC, and the between-class separability is characterized as the sum of distances between margin points and their neighboring points from different classes with the LRC. Therefore, the MFRC embodies the ideas of the LRC, Fisher analysis and manifold learning. Experiments on the FERET, PIE and AR datasets demonstrate the effectiveness of the MFRC.

Relevance and irrelevance graph based marginal Fisher analysis for image search reranking

In this paper, we propose a new supervised learning algorithm, which is named the Generalized Marginal Fisher Analysis (GMFA), to utilize the advantages of the Marginal Fisher Analysis (MFA) and the Generalized Singular Value Decomposition (GSVD) techniques for face recognition. The experimental results on several standard face databases demonstrate that GMFA outperforms LDA/Fisherface, LDA/GSVD and MFA.

Real-time identification of human activities in urban environments is increasingly becoming important in the context of public safety and national security. Distributed camera networks that provide multiple views of a scene are ideally suited for real-time action recognition. However, deployments of multi-camera based real-time action recognition systems have thus far been inhibited because of several practical issues and restrictive assumptions that are typically made such as the knowledge of a subjects orientation with respect to the cameras, the duration of each action and the conformation of a network deployment during the testing phase to that of a training deployment. In reality, action recognition involves classification of continuously streaming data from multiple views which consists of an interleaved sequence of various human actions. While there has been extensive research on machine learning techniques for action recognition from a single view, the issues arising in the fusion of data from multiple views for reliable action recognition have not received as much attention. In this thesis, I have developed a fusion framework for human action recognition using a multi-camera network that addresses these practical issues of unknown subject orientation, unknown view configurations, action interleaving and variable duration actions.;The proposed framework consists of two components: (1) a score-fusion technique that utilizes underlying view-specific supervised learning classifiers to classify an action within a given set of frames and (2) a sliding window technique that is used to parse a sequence of frames into multiple actions. The use of a score-fusion technique as opposed to a feature-level fusion of data from multiple views allows us to robustly classify actions even when camera configurations are arbitrary and different from training phase and at the same time reduces the required network bandwidth for data transmission permitting wireless deployments. Moreover, the proposed framework is independent of the underlying classifier that is used to generate scores for each action snippet and thus offers more flexibility compared to sequential approaches like Hidden Markov Models. The amount of training and parameterization is also significantly lower compared to HMM-based approaches. This Real-Time recognition system has been tested on 4 classifiers which are Linear Discriminant Analysis, Multinomial Naive Bayes, Logistic Regression and Support Vector Machines. Over 90% accuracy has been achieved by this system in Real-Time recognizing variable duration actions performed by the subject. The performance of the system is also shown to be robust to camera failures.

Majority of work in activity recognition using different machine learning and deep learning has shown very challenging results to monitor daily activities. Different datasets available on Web have been used to improve the results, still model fitness need to be verified in terms of different characteristics of matrix and error analysis. Dimensionality reduction (DR) of datasets improves the results of models due to pruning of dataset features. In this paper, we have introduced seven different machine learning models to improve the results. Proposed framework has used principle components analysis (PCA) and linear discriminant analysis (LDA) for dimensionality reduction of UCI-ML dataset. Results show that LDA is better than PCA. Kernel–SVM accuracy has increased from 95.39 to 96.23%. Naïve Bayes has shown 96.78% accuracy with dimensionality reduction. Simple dataset has shown low accuracy while dimensionality reduction has improved the performances of models. We have also introduced different challenges associated with machine learning models, fitness value, and future challenges. At the end of this work, we have done comparative study and error analysis of models.KeywordsClassificationDimensionality reductionMachine learning (ML)LDAPCAAccuracyHuman activity recognition (HAR)

A robust and unobtrusive human activity recognition system is essential to a multitude of applications, such as health care, active assisted living, robotics, sports, and tele-immersion. Existing well-performing activity recognition methods are either vision- or wearable sensor-based. However, they are not fully passive. In this paper, we develop WiHAR-an unobtrusive Wi-Fi-based activity recognition system. WiHAR uses the Wi-Fi network interface card to capture the channel state information (CSI) data. These CSI data are effectively processed, and then amplitude and phase information is used to obtain the spectrogram. In the subsequent step, the time-variant mean Doppler shift (MDS) caused by the human body movements in the radio signals before their arrival at the receiver is estimated. The MDS is used to extract time and frequency domain features that are needed to train the supervised learning algorithms (i.e., decision tree, linear discriminant analysis, and support vector machines (SVM)) to assess the performance of the WiHAR. Our results show that WiHAR combined with SVM achieves 96.2% recognition accuracy on the data set consisting of 9 participants where each participant performed four activities including: walking, falling, picking up an object from the ground, and sitting on a chair.

Feature extraction and classification are two key steps for activity recognition in a smart home environment. In this work, we performed a new hybrid model using Temporal or Spatial Features (TF or SF) with the PCA-LDA-WSVM classifier. The last method combines two methods for feature extraction: Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA) followed by Weighted SVM Classifier. This classifier is used to handle the problem of imbalanced activity data from sensor readings. The experiments that were implemented on multiple real-world datasets, showed the effectiveness of TF and SF attributes combined with PCA-LDA-WSVM in activity recognition.

Traditional supervised multiple kernel learning (MKL) for dimensionality reduction is generally an extension of kernel discriminant analysis (KDA), which has some restrictive assumptions. In addition, they generally are based on graph embedding framework. A more general multiple kernel-based dimensionality reduction algorithm, called multiple kernel marginal Fisher analysis (MKL-MFA), is presented for supervised nonlinear dimensionality reduction combined with ratio-race optimization problem. MKL-MFA aims at relaxing the restrictive assumption that the data of each class is of a Gaussian distribution and finding an appropriate convex combination of several base kernels. To improve the efficiency of multiple kernel dimensionality reduction, the spectral regression frameworks are incorporated into the optimization model. Furthermore, the optimal weights of predefined base kernels can be obtained by solving a different convex optimization. Experimental results on benchmark datasets demonstrate that MKL-MFA outperforms the state-of-the-art supervised multiple kernel dimensionality reduction methods.

Marginal Fisher Analysis(MFA) is a typical supervised subspace embedding method which has been used in dimensionality reduction. The projection matrixes are obtained by maximizing the intraclass compactness and simultaneously minimizing the intraclass separability. But in practical applications, no sufficient labeled training samples with prior knowledge was provided, so unlabeled image data are eager for incorporating in subspace learning algorithm to improve the identification accuracy. In this paper, we propose a semi supervised learning algorithm, which is called semi-supervised Marginal Fisher Analysis(SMFA). Not only the labeled data points are used to maximize the separability between different classes, but also the unlabeled data points are used to estimate the intrinsic geometric structure of the data. Therefore, we design a discriminant function which is as smooth as possible on the data manifold. Experimental results demonstrate that our SMFA algorithm outperforms the start-of-art methods.

This paper develops a supervised discriminant technique based on graph embedding, called maximum inter-class and marginal discriminant embedding (MIMDE) for feature and classification in high-dimensional data space. In graph embedding, our objective is to find a linear transform matrix to make the samples in the same class as compact as possible and the samples belong to the different classes as dispersed as possible through local property (intra-class compactness graph and inter-class separability graph) and marginal property (margin separability graph). This characteristic makes MIMDE more intuitive and more powerful than marginal Fisher analysis which not considered inter-class separability graph. Experimental results on ORL and AR face databases show the effectiveness of the proposed method.