Integration, transformation, dataset augmentation and quality control for intermediate representation

• Grant number: 19/06280-1
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: May 01, 2019
• End date: June 30, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Roberto Marcondes Cesar Junior
• Grantee: Hamed Yazdanpanah
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery, AP.TEM

Abstract

Many machine learning problems involve more than a single data source related to the problemof interest. For instance, if one is aimed at developing rich city model, datasets can be obtaineddescribing not only the plan of the streets, avenues, and roads, but also visual appearance fromonline cameras or street views, the population density along the several districts, the informationabout the geography of the region (including the existence of lakes, coast, mountains, etc.), theeconomy of the region among many other important related aspects. Such dataintegration has been considered strategic in recent urban informatics literature as well as otherfields. However, these datasets are often obtained and organized independently and have varyingdegrees of completeness and quality. Equally important is the fact that such datasets are notdirectly useful, demanding transformations in order to be more effectively analyzed given specificapplications. In the case of the previous example, the databases representing the streets and avenuesare often organized in CAD structures representing streets by polylines with control points definedby street intersections or high curvature points, while a more powerful representation would be tohave a graph or network containing only the former type of control points. So, it is necessary toremove the latter points, while performing a consistency checking.The integration of datasets corresponds to a critical task, because it is necessary to integratethe data in each independent database into a coherent whole. In the case of the previous example,it would be necessary to integrate the geographical coordinates into the control points deningthe streets. Frequently, such an integration demands incorporating into the processing a relativelyhigh level of intelligence about the data, objectives, and application. It is important to have commonmathematical/computational intermediate representations to perform meaningful integration.These two critical tasks, integration and transformation, therefore define the kernel of the presentapproach, as represented in the diagram in Figure 2 of the Thematic Project. Two particular topicsare of interest: dataset augmentation and quality control.

Scientific publications

(11)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

LIM, MARKUS V. S.; DINIZ, PAULO S. R.; YAZDANPANAH, HAMED. Set-Membership Constrained Frequency-Domain Algorithm. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, v. 68, n. 2, p. 797-801, FEB 2021. (19/06280-1, 15/22308-2)

YAZDANPANAH, HAMED. Improved feature least mean square algorithm. INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, v. N/A, p. 11-pg., 2022-11-17. (19/06280-1, 15/22308-2)

YAZDANPANAH, HAMED; APOLINARIO JR, JOSE A.. The Extended Feature LMS Algorithm: Exploiting Hidden Sparsity for Systems with Unknown Spectrum. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, v. 40, n. 1, JUN 2020. (15/22308-2, 19/06280-1)

DINIZ, PAULO S. R.; YAZDANPANAH, NAMED; LIMA, MARKUS V. S.; IEEE. Feature LMS Algorithm for Bandpass System Models. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), v. N/A, p. 5-pg., 2019-01-01. (19/06280-1, 15/22308-2)

YAZDANPANAH, HAMED; CARINI, ALBERTO; LIMA, MARKUS V. S.; IEEE. L-0-Norm Adaptive Volterra Filters. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), v. N/A, p. 5-pg., 2019-01-01. (19/06280-1, 15/22308-2)

YAZDANPANAH, HAMED; IEEE. FEATURE AFFINE PROJECTION ALGORITHMS. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, v. N/A, p. 5-pg., 2020-01-01. (19/06280-1, 15/22308-2)

YAZDANPANAH, HAMED; DINIZ, PAULO S. R.; LIMA, MARKUS V. S.. Improved simple set-membership affine projection algorithm for sparse system modelling: Analysis and implementation. IET SIGNAL PROCESSING, v. 14, n. 2, p. 81-88, APR 2020. (15/22308-2, 19/06280-1)

YAZDANPANAH, HAMED; DINIZ, PAULO S. R.; LIMA, MARKUS V. S.. Low-Complexity Feature Stochastic Gradient Algorithm for Block-Lowpass Systems. IEEE ACCESS, v. 7, p. 141587-141593, 2019. (15/22308-2, 19/06280-1)

CHAVES, GABRIEL S.; LIMA, MARKUS V. S.; YAZDANPANAH, HAMED; DINIZ, PAULO S. R.; FERREIRA, TADEU N.; IEEE. A Simple Sparsity-aware Feature LMS Algorithm. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), v. N/A, p. 5-pg., 2019-01-01. (19/06280-1, 15/22308-2)

YAZDANPANAH, HAMED; APOLINARIO, JOSE A., JR.; MATTHEWS, MB. FEATURE NORMALIZED LMS ALGORITHMS. CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, v. N/A, p. 4-pg., 2019-01-01. (19/06280-1, 15/22308-2)

YAZDANPANAH, HAMED; DINIZ, PAULO S. R.; LIMA, MARKUS V. S.. Feature Adaptive Filtering: Exploiting Hidden Sparsity. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, v. 67, n. 7, p. 2358-2371, JUL 2020. (19/06280-1, 15/22308-2)