Abstract: Estimating the 6D pose of objects is a core step for robot bin-picking tasks. The problem is that various objects are usually randomly stacked with heavy occlusion in real applications. In this work, we propose a method to regress 6D poses by predicting three points for each object in the 3D point cloud through deep learning. To solve the ambiguity of symmetric pose, we propose a labeling method to help the network converge better. Based on the predicted pose, an iterative method is employed for pose optimization. In real-world experiments, our method outperforms the classical approach in both precision and recall.
Abstract: The sensory stimuli from the urban environment are often distinguished as subtle structures that derive from experiencing the city. The experience of the urban environment is also related to the social relationships and memories that complete the 'urban eyescapes' and the way individuals can recall them. Despite the fact that the consideration of urban sensory stimuli is part of urban design, currently the account of visual experience in urban studies is hard to be identified. This article explores ways of recording how the senses mediate one's engagement with the urban environment. This study involves an experiment in the urban environment of the Copenhagen city centre, with 20 subjects performing a walking task. The aim of the experiment is to categorize the visual 'Bold Headlined Stimuli’ (BHS) of the examined environment, using eye-tracking techniques. The analysis allows us to identify the Headlining Stimuli Process, (HSP) in the select urban environment. HSP is significantly mediated by body mobility and perceptual memories and has shown how urban stimuli influence the intelligibility and the recalling patterns of the urban characteristics. The results have yielded a 'Bold Headline list' of stimuli related to: the spatial characteristics of higher preference; the stimuli that are relevant to livability; and the spatial dimensions easier to recall. The data of BHS will be used in cross-disciplinary city analysis. In the future, these results could be useful in urban design, to provide information on how urban space affects the human activities.
Abstract: Gestures play a major role in comprehension and
memory recall due to the fact that aid the efficient channel of
the meaning and support listeners’ comprehension and memory. In
the present study, the assistance of two kinds of gestures (iconic
and beat gestures) is tested in regards to memory and recall. The
hypothesis investigated here is whether or not iconic and beat gestures
provide assistance in memory and recall in Greek and in Greek
speakers’ second language. Two groups of participants were formed,
one comprising Greeks that reside in Athens and one with Greeks
that reside in Copenhagen. Three kinds of stimuli were used: A video
with words accompanied with iconic gestures, a video with words
accompanied with beat gestures and a video with words alone. The
languages used are Greek and English. The words in the English
videos were spoken by a native English speaker and by a Greek
speaker talking English. The reason for this is that when it comes to
beat gestures that serve a meta-cognitive function and are generated
according to the intonation of a language, prosody plays a major
role. Thus, participants that have different influences in prosody may
generate different results from rhythmic gestures. Memory recall was
assessed by asking the participants to try to remember as many
words as they could after viewing each video. Results show that
iconic gestures provide significant assistance in memory and recall
in Greek and in English whether they are produced by a native or
a second language speaker. In the case of beat gestures though, the
findings indicate that beat gestures may not play such a significant
role in Greek language. As far as intonation is concerned, a significant
difference was not found in the case of beat gestures produced by a
native English speaker and by a Greek speaker talking English.
Abstract: In order to retrieve images efficiently from a large
database, a unique method integrating color and texture features
using genetic programming has been proposed. Opponent color
histogram which gives shadow, shade, and light intensity invariant
property is employed in the proposed framework for extracting color
features. For texture feature extraction, fast discrete curvelet
transform which captures more orientation information at different
scales is incorporated to represent curved like edges. The recent
scenario in the issues of image retrieval is to reduce the semantic gap
between user’s preference and low level features. To address this
concern, genetic algorithm combined with relevance feedback is
embedded to reduce semantic gap and retrieve user’s preference
images. Extensive and comparative experiments have been conducted
to evaluate proposed framework for content based image retrieval on
two databases, i.e., COIL-100 and Corel-1000. Experimental results
clearly show that the proposed system surpassed other existing
systems in terms of precision and recall. The proposed work achieves
highest performance with average precision of 88.2% on COIL-100
and 76.3% on Corel, the average recall of 69.9% on COIL and 76.3%
on Corel. Thus, the experimental results confirm that the proposed
content based image retrieval system architecture attains better
solution for image retrieval.
Abstract: Optimal feeding, including optimal micronutrient
intake, becomes one of the ways to overcome the long-term
consequences of undernutrition. Macronutrient and micronutrient
intake were important to a rapid growth and development of young
children. The study objective was to assess macro and micronutrient
intake and its adequacy in children aged 12-23 months. This survey
was a cross-sectional study, involving 83 caregivers with children
aged 12-23 months old in Senen Sub-district, Central Jakarta selected
through simple random sampling. Data on nutrient intake was
obtained through interview using single 24-hour recall. Repeated 24-
hour recall to sub-sample was done to estimate the proportion of
nutrient inadequacy. The highest prevalence of nutrient inadequacy
was iron (52.4%), followed by vitamin C (30.9%) and zinc (28.8%).
Almost 12% children had inadequate energy intake. More than half
of children (62.6%) were anemic (25.3% were severely anemic).
Micronutrient inadequacy, especially iron, was more problematic
than macronutrient inadequacy in the study area.
Abstract: Reformulating the user query is a technique that aims to improve the performance of an Information Retrieval System (IRS) in terms of precision and recall. This paper tries to evaluate the technique of query reformulation guided by an external resource for Arabic texts. To do this, various precision and recall measures were conducted and two corpora with different external resources like Arabic WordNet (AWN) and the Arabic Dictionary (thesaurus) of Meaning (ADM) were used. Examination of the obtained results will allow us to measure the real contribution of this reformulation technique in improving the IRS performance.
Abstract: Today-s children, who are born into a more colorful,
more creative, more abstract and more accessible communication
environment than their ancestors as a result of dizzying advances in
technology, have an interesting capacity to perceive and make sense
of the world. Millennium children, who live in an environment where
all kinds of efforts by marketing communication are more intensive
than ever are, from their early childhood on, subject to all kinds of
persuasive messages. As regards advertising communication, it
outperforms all the other marketing communication efforts in
creating little consumer individuals and, as a result of processing of
codes and signs, plays a significant part in building a world of seeing,
thinking and understanding for children. Children who are raised with
metaphorical expressions such as tales and riddles also meet that fast
and effective meaning communication in advertisements.
Children-s perception of metaphors, which help grasp the “product
and its promise" both verbally and visually and facilitate association
between them is the subject of this study. Stimulating and activating
imagination, metaphors have unique advantages in promoting the
product and its promise especially in regard to print advertisements,
which have certain limitations. This study deals comparatively with
both literal and metaphoric versions of print advertisements
belonging to various product groups and attempts to discover to what
extent advertisements are liked, recalled, perceived and are
persuasive. The sample group of the study, which was conducted in
two elementary schools situated in areas that had different socioeconomic
features, consisted of children aged 12.
Abstract: Field Association (FA) terms are a limited set of discriminating terms that give us the knowledge to identify document fields which are effective in document classification, similar file retrieval and passage retrieval. But the problem lies in the lack of an effective method to extract automatically relevant Arabic FA Terms to build a comprehensive dictionary. Moreover, all previous studies are based on FA terms in English and Japanese, and the extension of FA terms to other language such Arabic could be definitely strengthen further researches. This paper presents a new method to extract, Arabic FA Terms from domain-specific corpora using part-of-speech (POS) pattern rules and corpora comparison. Experimental evaluation is carried out for 14 different fields using 251 MB of domain-specific corpora obtained from Arabic Wikipedia dumps and Alhyah news selected average of 2,825 FA Terms (single and compound) per field. From the experimental results, recall and precision are 84% and 79% respectively. Therefore, this method selects higher number of relevant Arabic FA Terms at high precision and recall.
Abstract: In this study, we examined gender differences in: (1) a
flexible remembering task, that asked for episodic memory decisions
at an item-specific versus category-based level, and (2) the retrieval
specificity of autobiographical memory during free recall.
Differences favouring women were found on both measures.
Furthermore, a significant association was observed, across gender
groups, between level of specificity in the autobiographical memory
interview and sensitivity to gist on the flexible remembering task.
These results suggest that similar cognitive processes may partially
contribute to both the ability for specific autobiographical recall and
the capacity for inhibition of gist-information on the flexible
remembering task.
Abstract: Text data mining is a process of exploratory data
analysis. Classification maps data into predefined groups or classes.
It is often referred to as supervised learning because the classes are
determined before examining the data. This paper describes proposed
radial basis function Classifier that performs comparative crossvalidation
for existing radial basis function Classifier. The feasibility
and the benefits of the proposed approach are demonstrated by means
of data mining problem: direct Marketing. Direct marketing has
become an important application field of data mining. Comparative
Cross-validation involves estimation of accuracy by either stratified
k-fold cross-validation or equivalent repeated random subsampling.
While the proposed method may have high bias; its performance
(accuracy estimation in our case) may be poor due to high variance.
Thus the accuracy with proposed radial basis function Classifier was
less than with the existing radial basis function Classifier. However
there is smaller the improvement in runtime and larger improvement
in precision and recall. In the proposed method Classification
accuracy and prediction accuracy are determined where the
prediction accuracy is comparatively high.
Abstract: As in today's semiconductor industries test costs can make up to 50 percent of the total production costs, an efficient test error detection becomes more and more important. In this paper, we present a new machine learning approach to test error detection that should provide a faster recognition of test system faults as well as an improved test error recall. The key idea is to learn a classifier ensemble, detecting typical test error patterns in wafer test results immediately after finishing these tests. Since test error detection has not yet been discussed in the machine learning community, we define central problem-relevant terms and provide an analysis of important domain properties. Finally, we present comparative studies reflecting the failure detection performance of three individual classifiers and three ensemble methods based upon them. As base classifiers we chose a decision tree learner, a support vector machine and a Bayesian network, while the compared ensemble methods were simple and weighted majority vote as well as stacking. For the evaluation, we used cross validation and a specially designed practical simulation. By implementing our approach in a semiconductor test department for the observation of two products, we proofed its practical applicability.