Fuzziness-based active learning framework to enhance hyperspectral image classification performance for discriminative and generative classifiers.

Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said problem, we propose a fuzziness-based active learning framework (FALF), in which we implement the idea of selecting optimal training samples to enhance generalization performance for two different kinds of classifiers, discriminative and generative (e.g. SVM and KNN). The optimal samples are selected by first estimating the boundary of each class and then calculating the fuzziness-based distance between each sample and the estimated class boundaries. Those samples that are at smaller distances from the boundaries and have higher fuzziness are chosen as target candidates for the training set. Through detailed experimentation on three publically available datasets, we showed that when trained with the proposed sample selection framework, both classifiers achieved higher classification accuracy and lower processing time with the small amount of training data as opposed to the case where the training samples were selected randomly. Our experiments demonstrate the effectiveness of our proposed method, which equates favorably with the state-of-the-art methods.

A Novel Maximum Entropy Markov Model for Human Facial Expression Recognition.

Research in video based FER systems has exploded in the past decade. However, most of the previous methods work well when they are trained and tested on the same dataset. Illumination settings, image resolution, camera angle, and physical characteristics of the people differ from one dataset to another. Considering a single dataset keeps the variance, which results from differences, to a minimum. Having a robust FER system, which can work across several datasets, is thus highly desirable. The aim of this work is to design, implement, and validate such a system using different datasets. In this regard, the major contribution is made at the recognition module which uses the maximum entropy Markov model (MEMM) for expression recognition. In this model, the states of the human expressions are modeled as the states of an MEMM, by considering the video-sensor observations as the observations of MEMM. A modified Viterbi is utilized to generate the most probable expression state sequence based on such observations. Lastly, an algorithm is designed which predicts the expression state from the generated state sequence. Performance is compared against several existing state-of-the-art FER systems on six publicly available datasets. A weighted average accuracy of 97% is achieved across all datasets.

Human facial expression recognition using stepwise linear discriminant analysis and hidden conditional random fields.

This paper introduces an accurate and robust facial expression recognition (FER) system. For feature extraction, the proposed FER system employs stepwise linear discriminant analysis (SWLDA). SWLDA focuses on selecting the localized features from the expression frames using the partial F-test values, thereby reducing the within class variance and increasing the low between variance among different expression classes. For recognition, the hidden conditional random fields (HCRFs) model is utilized. HCRF is capable of approximating a complex distribution using a mixture of Gaussian density functions. To achieve optimum results, the system employs a hierarchical recognition strategy. Under these settings, expressions are divided into three categories based on parts of the face that contribute most toward an expression. During recognition, at the first level, SWLDA and HCRF are employed to recognize the expression category; whereas, at the second level, the label for the expression within the recognized category is determined using a separate set of SWLDA and HCRF, trained just for that category. In order to validate the system, four publicly available data sets were used, and a total of four experiments were performed. The weighted average recognition rate for the proposed FER approach was 96.37% across the four different data sets, which is a significant improvement in contrast to the existing FER methods.

Context representation and fusion: advancements and opportunities.

The acceptance and usability of context-aware systems have given them the edge of wide use in various domains and has also attracted the attention of researchers in the area of context-aware computing. Making user context information available to such systems is the center of attention. However, there is very little emphasis given to the process of context representation and context fusion which are integral parts of context-aware systems. Context representation and fusion facilitate in recognizing the dependency/relationship of one data source on another to extract a better understanding of user context. The problem is more critical when data is emerging from heterogeneous sources of diverse nature like sensors, user profiles, and social interactions and also at different timestamps. Both the processes of context representation and fusion are followed in one way or another; however, they are not discussed explicitly for the realization of context-aware systems. In other words most of the context-aware systems underestimate the importance context representation and fusion. This research has explicitly focused on the importance of both the processes of context representation and fusion and has streamlined their existence in the overall architecture of context-aware systems' design and development. Various applications of context representation and fusion in context-aware systems are also highlighted in this research. A detailed review on both the processes is provided in this research with their applications. Future research directions (challenges) are also highlighted which needs proper attention for the purpose of achieving the goal of realizing context-aware systems.

Hierarchical recognition scheme for human facial expression recognition systems.

Over the last decade, human facial expressions recognition (FER) has emerged as an important research area. Several factors make FER a challenging research problem. These include varying light conditions in training and test images; need for automatic and accurate face detection before feature extraction; and high similarity among different expressions that makes it difficult to distinguish these expressions with a high accuracy. This work implements a hierarchical linear discriminant analysis-based facial expressions recognition (HL-FER) system to tackle these problems. Unlike the previous systems, the HL-FER uses a pre-processing step to eliminate light effects, incorporates a new automatic face detection scheme, employs methods to extract both global and local features, and utilizes a HL-FER to overcome the problem of high similarity among different expressions. Unlike most of the previous works that were evaluated using a single dataset, the performance of the HL-FER is assessed using three publicly available datasets under three different experimental settings: n-fold cross validation based on subjects for each dataset separately; n-fold cross validation rule based on datasets; and, finally, a last set of experiments to assess the effectiveness of each module of the HL-FER separately. Weighted average recognition accuracy of 98.7% across three different datasets, using three classifiers, indicates the success of employing the HL-FER for human FER.

Exploratory data analysis of acceleration signals to select light-weight and accurate features for real-time activity recognition on smartphones.

Smartphone-based activity recognition (SP-AR) recognizes users' activities using the embedded accelerometer sensor. Only a small number of previous works can be classified as online systems, i.e., the whole process (pre-processing, feature extraction, and classification) is performed on the device. Most of these online systems use either a high sampling rate (SR) or long data-window (DW) to achieve high accuracy, resulting in short battery life or delayed system response, respectively. This paper introduces a real-time/online SP-AR system that solves this problem. Exploratory data analysis was performed on acceleration signals of 6 activities, collected from 30 subjects, to show that these signals are generated by an autoregressive (AR) process, and an accurate AR-model in this case can be built using a low SR (20 Hz) and a small DW (3 s). The high within class variance resulting from placing the phone at different positions was reduced using kernel discriminant analysis to achieve position-independent recognition. Neural networks were used as classifiers. Unlike previous works, true subject-independent evaluation was performed, where 10 new subjects evaluated the system at their homes for 1 week. The results show that our features outperformed three commonly used features by 40% in terms of accuracy for the given SR and DW.

WEAMR-a weighted energy aware multipath reliable routing mechanism for hotline-based WSNs.

Reliable source to sink communication is the most important factor for an efficient routing protocol especially in domains of military, healthcare and disaster recovery applications. We present weighted energy aware multipath reliable routing (WEAMR), a novel energy aware multipath routing protocol which utilizes hotline-assisted routing to meet such requirements for mission critical applications. The protocol reduces the number of average hops from source to destination and provides unmatched reliability as compared to well known reactive ad hoc protocols i.e., AODV and AOMDV. Our protocol makes efficient use of network paths based on weighted cost calculation and intelligently selects the best possible paths for data transmissions. The path cost calculation considers end to end number of hops, latency and minimum energy node value in the path. In case of path failure path recalculation is done efficiently with minimum latency and control packets overhead. Our evaluation shows that our proposal provides better end-to-end delivery with less routing overhead and higher packet delivery success ratio compared to AODV and AOMDV. The use of multipath also increases overall life time of WSN network using optimum energy available paths between sender and receiver in WDNs.

A single tri-axial accelerometer-based real-time personal life log system capable of activity classification and exercise information generation.

Recording a personal life log (PLL) of daily activities is an emerging technology for u-lifecare and e-health services. In this paper, we present an accelerometer-based personal life log system capable of human activity classification and exercise information generation. In our system, we use a tri-axial accelerometer and a real-time activity recognition scheme in which a set of augmented features of accelerometer signals, processed with Linear Discriminant Analysis (LDA), is classified by our hierarchical artificial neural network classifier: in the lower level of the classifier, a state of an activity is recognized based on the statistical and spectral features; in the upper level, an activity is recognized with a set of augmented features including autoregressive (AR) coefficients, signal magnitude area (SMA), and tilt angles (TA). Upon the recognition of each activity, we further estimate exercise information such as energy expenditure based on Metabolic Equivalents (METS), step count, walking distance, walking speed, activity duration, etc. Our PLL system functions in real-time and all information generated from our system is archived in a daily-log database. By testing our system on seven different daily activities, we have obtained an average accuracy of 84.8% in activity recognition and generated their relative exercise information.

Accelerometer's position independent physical activity recognition system for long-term activity monitoring in the elderly.

Mobility is a good indicator of health status and thus objective mobility data could be used to assess the health status of elderly patients. Accelerometry has emerged as an effective means for long-term physical activity monitoring in the elderly. However, the output of an accelerometer varies at different positions on a subject's body, even for the same activity, resulting in high within-class variance. Existing accelerometer-based activity recognition systems thus require firm attachment of the sensor to a subject's body. This requirement makes them impractical for long-term activity monitoring during unsupervised free-living as it forces subjects into a fixed life pattern and impede their daily activities. Therefore, we introduce a novel single-triaxial-accelerometer-based activity recognition system that reduces the high within-class variance significantly and allows subjects to carry the sensor freely in any pocket without its firm attachment. We validated our system using seven activities: resting (lying/sitting/standing), walking, walking-upstairs, walking-downstairs, running, cycling, and vacuuming, recorded from five positions: chest pocket, front left trousers pocket, front right trousers pocket, rear trousers pocket, and inner jacket pocket. Its simplicity, ability to perform activities unimpeded, and an average recognition accuracy of 94% make our system a practical solution for continuous long-term activity monitoring in the elderly.

A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer.

Physical-activity recognition via wearable sensors can provide valuable information regarding an individual's degree of functional ability and lifestyle. In this paper, we present an accelerometer sensor-based approach for human-activity recognition. Our proposed recognition method uses a hierarchical scheme. At the lower level, the state to which an activity belongs, i.e., static, transition, or dynamic, is recognized by means of statistical signal features and artificial-neural nets (ANNs). The upper level recognition uses the autoregressive (AR) modeling of the acceleration signals, thus, incorporating the derived AR-coefficients along with the signal-magnitude area and tilt angle to form an augmented-feature vector. The resulting feature vector is further processed by the linear-discriminant analysis and ANNs to recognize a particular human activity. Our proposed activity-recognition method recognizes three states and 15 activities with an average accuracy of 97.9% using only a single triaxial accelerometer attached to the subject's chest.