Globally maximizing, locally minimizing: unsupervised discriminant projection with applications to face and palm biometrics

This paper develops an unsupervised discriminant projection (UDP) technique for dimensionality reduction of high-dimensional data in small sample size cases. UDP can be seen as a linear approximation of a multimanifolds-based learning framework which takes into account both the local and nonlocal quantities. UDP characterizes the local scatter as well as the nonlocal scatter, seeking to find a projection that simultaneously maximizes the nonlocal scatter and minimizes the local scatter. This characteristic makes UDP more intuitive and more powerful than the most up-to-date method, locality preserving projection (LPP), which considers only the local scatter for clustering or classification tasks. The proposed method is applied to face and palm biometrics and is examined using the Yale, FERET, and AR face image databases and the PolyU palmprint database. The experimental results show that UDP consistently outperforms LPP and PCA and outperforms LDA when the training sample size per class is small. This demonstrates that UDP is a good choice for real-world biometrics applications     

Learning to transform time series with a few examples

We describe a semi-supervised regression algorithm that learns to transform one time series into another time series given examples of the transformation. This algorithm is applied to tracking, where a time series of observations from sensors is transformed to a time series describing the pose of a target. Instead of defining and implementing such transformations for each tracking task separately, our algorithm learns a memoryless transformation of time series from a few example input-output mappings. The algorithm searches for a smooth function that fits the training examples and, when applied to the input time series, produces a time series that evolves according to assumed dynamics. The learning procedure is fast and lends itself to a closed-form solution. It is closely related to nonlinear system identification and manifold learning techniques. We demonstrate our algorithm on the tasks of tracking RFID tags from signal strength measurements, recovering the pose of rigid objects, deformable bodies, and articulated bodies from video sequences. For these tasks, this algorithm requires significantly fewer examples compared to fully-supervised regression algorithms or semi-supervised learning algorithms that do not take the dynamics of the output time series into account.     

Network visualization by semantic substrates

Networks have remained a challenge for information visualization designers because of the complex issues of node and link layout coupled with the rich set of tasks that users present. This paper offers a strategy based on two principles: (1) layouts are based on user-defined semantic substrates, which are non-overlapping regions in which node placement is based on node attributes, (2) users interactively adjust sliders to control link visibility to limit clutter and thus ensure comprehensibility of source and destination. Scalability is further facilitated by user control of which nodes are visible. We illustrate our semantic substrates approach as implemented in NVSS 1.0 with legal precedent data for up to 1122 court cases in three regions with 7645 legal citations     

Balancing systematic and flexible exploration of social networks

Social network analysis (SNA) has emerged as a powerful method for understanding the importance of relationships in networks. However, interactive exploration of networks is currently challenging because: (1) it is difficult to find patterns and comprehend the structure of networks with many nodes and links, and (2) current systems are often a medley of statistical methods and overwhelming visual output which leaves many analysts uncertain about how to explore in an orderly manner. This results in exploration that is largely opportunistic. Our contributions are techniques to help structural analysts understand social networks more effectively. We present SocialAction, a system that uses attribute ranking and coordinated views to help users systematically examine numerous SNA measures. Users can (1) flexibly iterate through visualizations of measures to gain an overview, filter nodes, and find outliers, (2) aggregate networks using link structure, find cohesive subgroups, and focus on communities of interest, and (3) untangle networks by viewing different link types separately, or find patterns across different link types using a matrix overview. For each operation, a stable node layout is maintained in the network visualization so users can make comparisons. SocialAction offers analysts a strategy beyond opportunism, as it provides systematic, yet flexible, techniques for exploring social networks     

High-automation proofs for properties of requirements models

We describe an approach and experimental results in the application of mechanized theorem proving to software requirements analysis. Serving as the test article was the embedded controller for SAFER, a backpack propulsion system used as a rescue device by NASA astronauts. SAFER requirements were previously formalized using the prototype verification system (PVS) during a NASA pilot project in formal methods, details of which appear in a NASA guidebook. This paper focuses on the formulation and proof of properties for the SAFER requirements model. To test the prospects for deductive requirements analysis, we used the PVS theorem prover to explore the upper limits of proof automation. A set of property classes was identified, with matching proof schemes later devised. After developing several PVS proof strategies (essentially prover macros), we obtained fully automatic proofs of 42 model properties. These results demonstrate how customized prover strategies can be used to automate moderate-complexity theorem proving for state machine models.     

The effects of personality traits,self-esteem,loneliness, and narcissism on Facebook use among university students

This study examined the relationship between three of the “Big Five” traits (neuroticism, extraversion, and openness), self-esteem, loneliness and narcissism, and Facebook use. Participants were 393 first year undergraduate psychology students from a medium-sized Australian university who completed an online questionnaire. Negative binomial regression models showed that students with higher openness levels reported spending more time on Facebook and having more friends on Facebook. Interestingly, students with higher levels of loneliness reported having more Facebook friends. Extraversion, neuroticism, self-esteem and narcissism did not have significant associations with Facebook use. It was concluded that students who are high in openness use Facebook to connect with others in order to discuss a wide range of interests, whereas students who are high in loneliness use the site to compensate for their lack of offline relationships.     

Local Convergence of the Lavrentiev Method for the Cauchy Problem via a Carleman Inequality

The purpose is to perform a sharp analysis of the Lavrentiev method applied to the regularization of the ill-posed Cauchy problem, set in the Steklov-Poincaré variational framework. Global approximation results have been stated earlier that demonstrate that the Lavrentiev procedure yields a convergent strategy. However, no convergence rates are available unless a source condition is assumed on the exact Cauchy solution. We pursue here bounds on the approximation (bias) and the noise propagation (variance) errors away from the incomplete boundary where instabilities are located. The investigation relies on a Carleman inequality that enables enhanced local convergence rates for both bias and variance errors without any particular smoothness assumption on the exact solution. These improved results allows a new insight on the behavior of the Lavrentiev solution, look similar to those established for the Quasi-Reversibility method in [Inverse Problems 25, 035005, 2009]. There is a case for saying that this sort of ??super-convergence?? is rather inherent to the nature of the Cauchy problem and any reasonable regularization procedure would enjoy the same locally super-convergent behavior.     

Segmentation of cervical cell nuclei in high-resolution microscopic images: A new algorithm and a web-based software framework

In order to automate cervical cancer screening tests, one of the most important and longstanding challenges is the segmentation of cell nuclei in the stained specimens. Though nuclei of isolated cells in high-quality acquisitions often are easy to segment, the problem lies in the segmentation of large numbers of nuclei with various characteristics under differing acquisition conditions in high-resolution scans of the complete microscope slides. We implemented a system that enables processing of full resolution images, and proposes a new algorithm for segmenting the nuclei under adequate control of the expert user. The system can work automatically or interactively guided, to allow for segmentation within the whole range of slide and image characteristics. It facilitates data storage and interaction of technical and medical experts, especially with its web-based architecture. The proposed algorithm localizes cell nuclei using a voting scheme and prior knowledge, before it determines the exact shape of the nuclei by means of an elastic segmentation algorithm. After noise removal with a mean-shift and a median filtering takes place, edges are extracted with a Canny edge detection algorithm. Motivated by the observation that cell nuclei are surrounded by cytoplasm and their shape is roughly elliptical, edges adjacent to the background are removed. A randomized Hough transform for ellipses finds candidate nuclei, which are then processed by a level set algorithm. The algorithm is tested and compared to other algorithms on a database containing 207 images acquired from two different microscope slides, with promising results.     

The influence of music on mood and performance while driving

Mood can influence our everyday behaviour and people often seek to reinforce, or to alter their mood, for example by turning on music. Music listening while driving is a popular activity. However, little is known about the impact of music listening while driving on physiological state and driving performance. In the present experiment, it was investigated whether individually selected music can induce mood and maintain moods during a simulated drive. In addition, effects of positive, negative, and no music on driving behaviour and physiological measures were assessed for normal and high cognitive demanding rides. Subjective mood ratings indicated that music successfully maintained mood while driving. Narrow lane width drives increased task demand as shown in effort ratings and increased swerving. Furthermore, respiration rate was lower during music listening compared to rides without music, while no effects of music were found on heart rate. Overall, the current study demonstrates that music listening in car influences the experienced mood while driving, which in turn can impact driving behaviour. PRACTITIONERS SUMMARY: Even though it is a popular activity, little is known about the impact of music while driving on physiological state and performance. We examined whether music can induce moods during high and low simulated drives. The current study demonstrates that in car music listening influences mood which in turn can impact driving behaviour. The current study shows that listening to music can positively impact mood while driving, which can be used to affect state and safe behaviour. Additionally, driving performance in high demand situations is not negatively affected by music.