1,721,015 research outputs found
A Bottom-up Strategy for Clustering Complex Datasets with Application to Language and Script Discrimination
No full textA bottom-up clustering algorithm can be used to extend a state-of-the-art method to partition datasets in groups of complex data. The algorithm has been applied to discriminate between documents in different languages and scripts
The Approximate Average Common Submatrix for Computing the Image Similarity
No full textThe similarity between images can be computed using a new method that compares image patches where a portion of pixels is omitted at regular intervals. The method is accurate and reduces execution time relative to conventional methods
A Deep Learning Approach for Predicting Air Pollutants on the Construction Site
No full textIn recent years, the problem of air pollution has become an urgent issue causing a meaningful impact on health and environment. In urban areas, one of the main sources of pollution is air pollution on construction sites. It is characterized by multiple pollutants, among which one of the most worrying harmful substances is suspended particulate (PM2.5), causing serious damage to human health and environment. Although different monitoring systems have been recently introduced for assessing the level of air pollutants on construction sites, predicting their diffusion over time has not been explored so far, which is relevant to preserve the health of workers and people surrounding the area. To overcome this limitation, we propose a new framework based on recurrent neural networks for monitoring and predicting the spread of air pollutants on construction sites, in particular PM2.5, from known environmental conditions. The framework is composed of the following steps: (i) data preprocessing, (ii) model training, (iii) model testing, and (iv) model deployment in the construction site. Results obtained on the test set prove the reliability and usability of the proposed framework for the construction sites
A knowledge representation framework for managing Leonardo Da Vinci’s Mona Lisa: case study of the hidden painting
No full textThis paper explores the use of Artificial Intelligence/Knowledge Representation methods for digitally modeling the cultural heritage items. It fully complies with the concept of “Cultural Heritage Digital Twin”, which is characterized by a “physical” component of the cultural entity, concerning style, dimension, name of the artist, execution time, etc., and by an “immaterial” component representing, among other things, the emotional and intangible messages transmitted by the entity. The “Narrative Knowledge Representation Language” (NKRL) is then been adopted for digitally representing the two components of the twin and its immaterial component in particular, due to its ability to represent in a simple but rigorous and efficient way complex situations and events, behaviors, attitudes, etc. An experiment concerning the “hidden painting” that lies beneath the Mona Lisa (“La Gioconda”) image on the same poplar panel has been then realized, showing that NKRL is able, in fact, to successfully provide a suitable representation of at least some of the intangible elements of the “visual narrative” represented by this still largely undeciphered portrait
Digitization of Forensic Engineering: Overview, Perspectives and New Challenges
No full textIn the last years, digitization of data and processes in the forensic field has started to flourish as a core aspect of computer science, due to the need of extracting, representing and storing the underlying information. The scope of application is wide and multidisciplinary, as the digitization process now fully involves all phases of the forensic process. Due to the recent innovations in the field of knowledge representation and data analytics, this paper provides a thorough methodological overview of the main digitizing approaches and algorithms within the so-called “Forensic Engineering”. Firstly, the two terms “Digitization” and “Forensic” will be introduced and defined. Then, the meaning and value of these two concepts combined together will be explored. Accordingly, an overview of the forensic digitization procedure will be provided and the importance that this digital transformation entails, in both scientific and innovation terms. Secondly, different examples of data-driven approaches and intelligent systems for knowledge extraction, representation and classification will be presented in multiple contexts of forensic engineering. Following a methodologic analysis of the main limitations of the existing methods, we will propose innovative and promising research directions in the field. Finally, many difficulties, due to Code requirements and Code of Practice approaches, will be pointed out in order to define a more practical approach for a common Legal Engineer
New Directions for Recognizing visual Patterns in Medical Imaging
No full textNew study directions are focused on the extraction and recognition of visual patterns from different types of medical images
Association rule mining for the usability of the CAPTCHA interfaces: a new study of multimedia systems
No full textThis paper presents an analysis of the CAPTCHA interfaces in terms of their usability to Internet users. The usability is represented by the time needed to the users for finding a solution to the CAPTCHA, which is called response time. Specifically, the analysis is focused on four examples of text and image-based CAPTCHA. The aim is to study the cognitive factors influencing the Internet users in finding a solution to these four CAPTCHA types. Accordingly, an experiment is conducted on 100 Internet users, characterized by demographic factors, such as age, gender, Internet experience, and education level. Each user is asked to solve the four CAPTCHA types, and the response time for each of them is registered. Collected data including demographic factors and response time is subjected to association rule mining, using the FP-Growth algorithm for extracting the association rules. They show the dependence of the response time on the co-occurrence of the demographic factors. Also, an additional statistical analysis is performed using the nonparametric one-way Kruskal Wallis’ test. Experiments comparing the proposed method with the earlier studies of the CAPTCHA usability show the novelty of the method for the understanding of usability of CAPTCHA interfaces, which is based on the cognitive factors that influence the response time
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Cottonwood Leaf Beetle Chrysomela scripta Fabricius (Insecta: Coleoptera: Chrysomelidae: Chrysomela)
No full textThe cottonwood leaf beetle is one of the most economically important pests of managed cottonwood, aspen, and some poplar and willow species. Often it is a severe pest of urban ornamental trees. This leaf feeder has several generations each year, may cause extensive leaf loss, and can consequently reduce stem volume up to 70%. This 6-page fact sheet was written by Amelio A. Chi and Russell F. Mizell, III, and published by the UF Department of Entomology and Nematology, June 2012.
EENY-519/IN936: Cottonwood Leaf Beetle Chrysomela scripta Fabricius (Insecta: Coleoptera: Chrysomelidae: Chrysomela) (ufl.edu
- …
