Data Mining - Concepts and Techniques.

Statistics for Spatial Data.

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

: The goal of this study is to determine variable relationships and a computational workflow that yield the highest quality of three-dimensional reconstructions in neutron imaging applications with reduced number of projections angles. Neutrons interact with matter primarily through the strong nuclear force providing unique image contrast modes. Accessing many of these contrast modes requires defining the energy of the neutron beam, resulting in long exposure times for a single two-dimensional projection image. To collect of order 100 tomograms at different neutron wavelengths within a reasonable time frame (less than 1 week) suggests the use of dose reduction tomography reconstruction algorithms. We identified and evaluated the main factors affecting the quality of the 3D tomographic reconstruction in the computational image workflow: the projection number, the reconstruction method, and the post-processing method. This study reports several relationships between 3D reconstruction quality metrics and acquisition time. Based on the established relationships, the performance of a seeded simultaneous iterative reconstruction technique (SIRT) yielded improved image quality and more accurate estimates of the reconstructed attenuation values compared to a SIRT without a priori information or a trained neural network based on a mixed scale dense network.

Assessment of Dose Reduction Strategies in Wavelength-selective Neutron Tomography

This work addresses the problems of (a) designing utilization measurements of trained artiﬁcial intelligence (AI) models and (b) explaining how training data are encoded in AI models based on those measurements. The problems are motivated by the lack of explainability of AI models in security and safety critical applications, such as the use of AI models for classiﬁcation of traﬃc signs in self-driving cars. We approach the problems by introducing theoretical underpinnings of AI model utilization measurement and understanding patterns in utilization-based class encodings of traﬃc signs at the level of computation graphs (AI models), subgraphs, and graph nodes. Conceptually, utilization is deﬁned at each graph node (computation unit) of an AI model based on the number and distribution of unique outputs in the space of all possible outputs (tensor-states). In this work, utilization measurements are extracted from AI models, which include poisoned and clean AI models. In contrast to clean AI models, the poisoned AI models were trained with traﬃc sign images containing systematic, physically realizable, traﬃc sign modiﬁcations (i.e., triggers ) to change a correct class label to another label in a presence of such a trigger . We analyze class encodings of such clean and poisoned AI models, and conclude with implications for trojan injection and detection.

AI Model Utilization Measurements For Finding Class Encoding Patterns

LipoPose: Adapting Cellpose to Lipid Nanoparticle Segmentation

This work addresses the problem of designing a scalable framework for archival appraisals of contemporary PDF documents. The motivation for our work is to provide an e-science solution that (a) fuses the independent research methodologies focusing on specific information types to one comprehensive analytical framework, (b) optimizes tradeoffs between computational requirements and preservation costs, and (b) bridges the small scale and large scale computational studies. The e-science solution presented here consists of (1) a methodology for comprehensive comparisons of contemporary documents containing text, images and vector graphics, (2) a framework for including 3D and 3D+time data sets into the appraisal analyses, (3) interfaces supporting exploratory archival appraisal analyses with small scale data sets, and (4) infrastructure supporting the transition from small scale to large scale computations using commodity and high performance computing resources. The novelty of our work is in designing methodologies, mathematical frameworks and prototypes for comprehensive and scalable document appraisals that include text, images, vector graphics, and high dimensional data.

/pdf/advanced-information-systems-for-archival-appraisals-of-5p6m446005.pdf

Advanced Information Systems for Archival Appraisals of Contemporary Documents

This paper addresses the problem of robust and automated synchronization of multiple audio and video signals. The
input signals are from a set of independent multimedia recordings coming from several camcorders and microphones.
While the camcorders are static, the microphones are mobile as they are attached to people. The motivation for
synchronization of all signals is to support studies and understanding of human interaction in a decision support
environment that have been limited so far due to the difficulties in automated processing of any observations during the
decision making sessions. The application of our work is to environments supporting decisions. The data sets for this
work have been acquired during training exercises of response teams, rescue workers, and fire fighters at multiple
locations.
The developed synchronization methodology for a set of independent multimedia recordings is based on introducing
aural and visual landmarks with a bell and room light switches. Our approach to synchronization is based on detecting
the landmarks in audio and video signals per camcorder and per microphone, and then fusing the results to increase
robustness and accuracy of the synchronization. We report synchronization results that demonstrate accuracy of
synchronization based on video and audio.

Peter Bajcsy

Papers

Assessment of Dose Reduction Strategies in Wavelength-selective Neutron Tomography

AI Model Utilization Measurements For Finding Class Encoding Patterns

LipoPose: Adapting Cellpose to Lipid Nanoparticle Segmentation

Advanced Information Systems for Archival Appraisals of Contemporary Documents

Robust video and audio-based synchronization of multimedia files