Jingying Chen

G-Hadoop: MapReduce across distributed data centers for data-intensive computing

Recently, the computational requirements for large-scale data-intensive analysis of scientific data have grown significantly. In High Energy Physics (HEP) for example, the Large Hadron Collider (LHC) produced 13 petabytes of data in 2010. This huge amount of data is processed on more than 140 computing centers distributed across 34 countries. The MapReduce paradigm has emerged as a highly successful programming model for large-scale data-intensive computing applications. However, current MapReduce implementations are developed to operate on single cluster environments and cannot be leveraged for large-scale distributed data processing across multiple clusters. On the other hand, workflow systems are used for distributed data processing across data centers. It has been reported that the workflow paradigm has some limitations for distributed data processing, such as reliability and efficiency. In this paper, we present the design and implementation of G-Hadoop, a MapReduce framework that aims to enable large-scale distributed computing across multiple clusters.

Natural Disaster Monitoring with Wireless Sensor Networks: A Case Study of Data-intensive Applications upon Low-Cost Scalable Systems

The wireless sensor network (WSN) technology has applied in monitoring natural disasters for more than one decade. Disasters can be closely monitored by augmenting a variety of sensors, and WSN has merits in (1) low cost, (2) quick response, and (3) salability and flexibility. Natural disaster monitoring with WSN is a well-known data intensive application for the high bandwidth requirements and stringent delay constraints. It manifests a typical paradigm of data-intensive application upon low-cost scalable system. In this study, we first assessed representative works in this area by classifying those in the domains of application of WSNs for disasters and optimization technologies significantly distinguishing these from general-purpose WSNs. We then described the design of an early warning system for geohazards in reservoir region, which relies on the WSN technology inspired by the existing work with focuses on issues of (1) supporting reliable data transmission, (2) handling huge data of heterogeneous sources and types, and (3) minimizing energy consumption. This study proposes a dynamic routing protocol, a method for network recovery, and a method for managing mobile nodes to enable real-time and reliable data transmission. The system incorporates data fusion and reconstruction approaches to bring together all data into a single view of the geohazard under monitoring. A distributed algorithm for joint optimal control of power and rate has been developed, which can improve utility of network (> 95 %) and to minimize the energy consumption (reduction by > 20 % in comparison with LEACH). Experimental results indicate the potentials of the proposed approaches in terms of adapting to the needs of early warning on geohazards.

Hybrid modelling and simulation of huge crowd over a hierarchical Grid architecture

The last decade has witnessed an explosion of the interest in technologies of large simulation with the rapid growth of both the complexity and the scale of problem domains. Modelling & simulation of crowd is a typical paradigm, especially when dealing with large crowd. On top of a hierarchical Grid simulation infrastructure, a simulation of evacuating tens of thousands of pedestrians in an urban area has been constructed. The simulation infrastructure can facilitate a large crowd simulation comprising models of different grains and various types in nature. A number of agent-based and computational models residing at two distinctive administrative domains operate together, which successfully presents the dynamics of the complex scenario at scales of both individual and crowd levels. Experimental results indicate that the proposed hybrid modelling & simulation approach can effectively cope with the size and complexity of a scenario involving a huge crowd.

Modeling and simulation for natural disaster contingency planning driven by high-resolution remote sensing images

Natural disasters occur unexpectedly and usually result in huge losses of life and property. How to effectively make contingency plans is an intriguing question constantly faced by governments and experts. Human rescue operations are the most critical issue in contingency planning. A natural disaster scenario is, in general, highly complicated and dynamic. Modeling and simulation technologies have been gaining considerable momentum in investigating natural disaster scenarios to enable contingency planning. However, existing MS and (2) the absence of methods and platforms to describe the collective behaviors of people in disaster situations. Considering these problems, an M&S framework for human rescue operations in a typical natural disaster, i.e., a landslide, has been developed in this study. The framework consists of three modules: (1) remote sensing information extraction, (2) landslide simulation, and (3)crowd simulation. The crowd simulation module is driven by the real/virtual data provided by the former modules. A number of simulations (using the Zhouqu landslide as an example) have been performed to study human relief operations spontaneously and under manipulation, with the effect of contingency plans highlighted. The experimental results demonstrate that (1) the simulation framework is an effective tool for contingency planning, and (2) real data can make the simulation outputs more meaningful. We enable evaluation of contingency plans using modelling and simulation technology.We model crowd behaviors under natural disasters.We develop a DDDAS simulation framework with the support of high resolution remote sensing information.

Towards Improving Social Communication Skills With Multimodal Sensory Information

How to improve social communication skills for children, especially those with social communication difficulties such as attention deficit/hyperactivity disorder, has long been a challenge faced by researchers and therapists. Recent research indicates that computer-assisted approaches may be effective in addressing this issue. This study aimed to understand childrens behaviors and then provide appropriate support to improve their social communication skills. We have established an intelligent system, inside which a child can freely play interactive social skills games with virtual characters. The virtual characters can adjust their own behaviors by adapting to the childs cognitive state (e.g., focus of attention) and affective state (e.g., happiness or surprise). The childs behavior is identified in real-time by recognition of multimodal sensory information, which includes head pose and eye gaze estimation, gesture detection, and affective state detection supported by a series of algorithms proposed in this study. Furthermore, this intelligent system has been enabled in a nonintrusive manner using a novel approach of multicamera surveillance to provide the child with natural interaction with the system. Experimental results show the system can estimate a users attention and affective states with correctness rates of 93% and 91.3%, respectively. The results obtained suggest that the methods have strong potential as alternative methods for sensing human behavior and providing appropriate support.

Facial expression recognition using geometric and appearance features

A novel method using hybrid geometric and appearance features of the difference between the neutral and fully expressive facial expression images is proposed for facial expression recognition in this paper. The difference tends to emphasize the facial parts that are changed from the neutral to expressive face and eliminate in that way the identity of the facial image. The hybrid features include facial feature point displacements and local texture differences between the normalized neutral and expressive facial expression images. The proposed method achieved an average accuracy of 95% in the extended Cohn-Kanade database with a Support Vector Machine (SVM) classification method.

A hybrid intelligence-aided approach to affect-sensitive e-learning

E-Learning has revolutionized the delivery of learning through the support of rapid advances in Internet technology. Compared with face-to-face traditional classroom education, e-learning lacks interpersonal and emotional interaction between students and teachers. In other words, although a vital factor in learning that influences a human’s ability to solve problems, affect has been largely ignored in existing e-learning systems. In this study, we propose a hybrid intelligence-aided approach to affect-sensitive e-learning. A system has been developed that incorporates affect recognition and intervention to improve the learner’s learning experience and help the learner become better engaged in the learning process. The system recognizes the learner’s affective states using multimodal information via hybrid intelligent approaches, e.g., head pose, eye gaze tracking, facial expression recognition, physiological signal processing and learning progress tracking. The multimodal information gathered is fused based on the proposed affect learning model. The system provides online interventions and adapts the online learning material to the learner’s current learning state based on pedagogical strategies. Experimental results show that interest and confusion are the most frequently occurring states when a learner interacts with a second language learning system and those states are highly related to learning levels (easy versus difficult) and outcomes. Interventions are effective when a learner is disengaged or bored and have been shown to help learners become more engaged in learning.

Robust head pose estimation using Dirichlet-tree distribution enhanced random forests

Head pose estimation (HPE) is important in human-machine interfaces. However, various illumination, occlusion, low image resolution and wide scene make the estimation task difficult. Hence, a Dirichlet-tree distribution enhanced Random Forests approach (D-RF) is proposed in this paper to estimate head pose efficiently and robustly in unconstrained environment. First, positive/negative facial patch is classified to eliminate influence of noise and occlusion. Then, the D-RF is proposed to estimate the head pose in a coarse-to-fine way using more powerful combined texture and geometric features of the classified positive patches. Furthermore, multiple probabilistic models have been learned in the leaves of the D-RF and a composite weighted voting method is introduced to improve the discrimination capability of the approach. Experiments have been done on three standard databases including two public databases and our lab database with head pose spanning from -90? to 90? in vertical and horizontal directions under various conditions, the average accuracy rate reaches 76.2% with 25 classes. The proposed approach has also been evaluated with the low resolution database collected from an overhead camera in a classroom, the average accuracy rate reaches 80.5% with 15 classes. The encouraging results suggest a strong potential for head pose and attention estimation in unconstrained environment.

Comprehensive Association Rules Mining of Health Examination Data with an Extended FP-Growth Method

With the booming of social media and health informatics, there exists a pressing need for a powerful tool to sustain comprehensive analysis of public and personal health information. In particular, it should be able (1) to maximize the discovery of association rules amongst data items and (2) to handle the rapid growing data scale. The FP-Growth algorithm is a salient association rule learning method in exploring potential relation in database possibly with a lack of priori knowledge. It has the merits of low time & space complexity, whereas it cannot handle negative association rules which is necessary in comprehensive mining of health data. In order to enable comprehensive discovery of association rules, this study extends the FP-Growth algorithm to mine both positive and negative frequent patterns, namely the PNFP-Growth framework. The extended approach also adopts a prune strategy to filter out misleading patterns to the most by correlating the negative data items and the positive ones. Experiments had been performed to evaluate the performance of the PNFP-Growth over a public data set and a database consisting of thousands of people’s real health examination information (collected within 5 years from the date of this publication). The results indicate that (1) the PNFP-Growth can excavate more patterns than the traditional counterpart does while it is still highly efficient, and (2) the analysis upon the health examination data is informative and well complies with the clinical practices, e.g., more than 30 % people suffering from hypertension are having high systolic pressure and liver problems.

Deep peak-neutral difference feature for facial expression recognition

Facial expression recognition (FER) is important in vision-related applications. Deep neural networks demonstrate impressive performance for face recognition; however, it should be noted that this method relies heavily on a great deal of manually labeled training data, which is not available for facial expressions in real-world applications. Hence, we propose a powerful facial feature called deep peak–neutral difference (DPND) for FER. DPND is defined as the difference between two deep representations of the fully expressive (peak) and neutral facial expression frames. The difference tends to emphasize the facial parts that are changed in the transition from the neutral to the expressive face and to eliminate the face identity information retained in the fine-tuned deep neural network for facial expression, the network has been trained on large-scale face recognition dataset. Furthermore, unsupervised clustering and semi-supervised classification methods are presented to automatically acquire the neutral and peak frames from the expression sequence. The proposed facial expression feature achieved encouraging results on public databases, which suggests that it has strong potential to recognize facial expressions in real-world applications.