Improving image annotation via useful representative feature selection

This paper describes the automatic assignment of images into classes described by individual keywords provided with the Corel data set. Automatic image annotation technology aims to provide an efficient and effective searching environment for users to query their images more easily, but current image retrieval systems are still not very accurate when assigning images into a large number of keyword classes. Noisy features are the main problem, causing some keywords never to be assigned to their correct images. This paper focuses on improving image classification, first by selection of features to characterise each image, and then the selection of the most suitable feature vectors as training data. A Pixel Density filter (PDfilter) and Information Gain (IG) are proposed to perform these respective tasks. We filter out the noisy features so that groups of images can be represented by their most important values. The experiments use hue, saturation and value (HSV) colour feature space to categorise images according to one of 190 concrete keywords or subsets of these. The study shows that feature selection through the PDfilter and IG can improve the problem of spurious similarity.

The "Humpty Dumpty Problem" in the Study of Early Cognitive Development: Putting the Infant Back Together Again

ABSTRACT— In this article, I propose that the big question for the field of infant cognitive development is best characterized as the "Humpty Dumpty problem": Now that we have studied cognitive abilities in isolation, how do we put the developing cognitive system (and the infant) back together again? This problem is significant because cognitive abilities do not occur in isolation. Infants remember the items they have attended to and perceived, and their emotional state will influence their perception and representation of the events they encounter. Moreover, by examining the development of the whole cognitive system, or the whole child, we gain a deeper understanding of mechanisms developmental change. Thus, the big question for the study of infant cognition is like the question confronting all the king's horses and all the king's men: How do we put the infant's cognitive system back together again?     

Nutritional habits and motivations to eat after a palatable pre-load

A representative sample of college students was surveyed about nutritional habits and motivations to eat. Females were more likely to report dieting, being overweight, reading nutritional labels, eating healthy meals, as well as hungering for and consuming lower fat foods compared to males. Males reported a greater hunger for and consumption of candy bars compared to females. Thus, females may not be as ambivalent about eating sweet or higher fat foods as previously suggested. The experimental manipulation involved exposing subjects to either candy before the survey, candy with the survey, or just the survey with no candy exposure. Females exposed to the candy preload indicated an increased hunger for fruits and vegetables compared to female controls. Portions of this research have been presented at the 1999 annual meeting of the Eastern Psychological Association in Providence, RI. The authors would like to thank Mr. Steve Lukasik and Ms. Christie Piedmont for their assistance on this project.     

Self-reported measures of appetite in relation to verbal cues about many foods

In the present study a representative sample of students from a general college population were exposed to a list of written food cues and asked to rate each of the foods according to its nutritional value. Subjects who were exposed to the food list subsequently reported increases in hunger, desire to eat, and number of foods currently hungry for, as well as reduced fullness, compared to controls who were not exposed to the food list. Also, there was a trend for the food-cued subjects to report hunger for lower fat foods compared to the controls. The results are discussed in terms of previous research and suggestions for future research are provided.     

Individual Piagetian Epistemological Development of Children from Ages 6 to 11

This long-term study of children from ages 6 to 11 was undertaken to support the patterns of cognitive development inferred from Piaget's work and its short-term statistical replications. Several Piagetian tasks were used individually with 48 first graders, some of the same and new tasks with 43 of the same children as third graders, and two new tasks with 38 of the same children as fifth graders. Pearson product-moment coefficients indicated that uses of the clinical tasks in the study agreed significantly with those in the literature. In 33 individual line graphs, the average age (as indicated in the literature) for the most difficult task performed by a child at each level was compared with the actual age for the child's performance. Although individual aberrations in rates and patterns of cognitive development were observed, the graphic data supported the main hypothesis of the study.